Instructions to use vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt")
model = AutoModelForMultimodalLM.from_pretrained("vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt

SGLang

How to use vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt with Docker Model Runner:
```
docker model run hf.co/vroomfondel/Qwen3.8-27B-NVFP4-ModelOpt
```

Qwen3.8-27B-NVFP4-ModelOpt / .quant_summary.txt

vroomfondel

Upload NVFP4 (ModelOpt) quantization

5da9eb4 verified about 2 months ago

Raw History Blame Contribute Delete

335 kB

	model.visual.patch_embed.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.patch_embed.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.patch_embed.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.pos_embed.weight_quantizer TensorQuantizer(disabled)
	model.visual.pos_embed.input_quantizer HardDisabledTensorQuantizer(disabled)
	model.visual.pos_embed.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.0.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.1.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.2.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.3.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.4.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.5.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.6.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.7.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.8.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.9.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.10.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.11.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.12.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.13.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.14.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.15.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.16.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.17.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.18.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.19.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.20.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.21.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.22.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.23.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.24.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.25.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.norm1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.norm1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.norm2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.norm2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.qkv.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.qkv.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.qkv.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.proj.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.proj.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.proj.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.k_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.v_bmm_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.attn.softmax_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.mlp.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.mlp.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.mlp.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.mlp.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.mlp.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.blocks.26.mlp.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.visual.merger.norm.input_quantizer TensorQuantizer(disabled)
	model.visual.merger.norm.output_quantizer TensorQuantizer(disabled)
	model.visual.merger.linear_fc1.input_quantizer TensorQuantizer(disabled)
	model.visual.merger.linear_fc1.output_quantizer TensorQuantizer(disabled)
	model.visual.merger.linear_fc1.weight_quantizer TensorQuantizer(disabled)
	model.visual.merger.linear_fc2.input_quantizer TensorQuantizer(disabled)
	model.visual.merger.linear_fc2.output_quantizer TensorQuantizer(disabled)
	model.visual.merger.linear_fc2.weight_quantizer TensorQuantizer(disabled)
	model.language_model.embed_tokens.weight_quantizer TensorQuantizer(disabled)
	model.language_model.embed_tokens.input_quantizer HardDisabledTensorQuantizer(disabled)
	model.language_model.embed_tokens.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.84e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.35e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.36e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.38e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.88e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.22e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.88e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.63e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.49e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.0.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.0.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.80e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.50e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.48e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.34e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.34e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.34e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.66e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.09e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.31e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.09e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.14e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.44e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.1.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.1.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.41e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.16e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.49e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.56e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.02e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.56e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.48e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.72e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.57e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.72e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.74e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.2.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.2.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.19e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.20e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.10e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.27e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.31e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.44e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.59e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.50e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.68e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.50e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.74e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.04e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.3.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.3.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.72e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.28e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.38e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.11e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.95e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.11e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.61e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.53e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.87e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.53e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.68e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.62e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.4.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.4.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.36e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.56e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.38e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.19e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.44e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.22e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.22e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.34e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.06e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.5.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.5.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.87e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.34e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.10e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.60e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.62e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.31e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.62e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.05e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.6.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.6.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.20e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.73e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.97e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.06e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.36e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.46e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.72e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.03e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.29e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.03e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.37e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.62e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.7.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.7.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.37e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.25e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.15e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.75e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.23e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.75e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.48e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.8.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.8.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.38e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.88e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.25e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.14e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.14e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.94e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.76e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.94e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.25e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.28e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.9.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.9.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.47e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.04e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.14e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.61e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.14e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.73e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.09e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.09e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.26e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.32e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.10.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.10.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.70e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.00e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.83e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.56e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.00e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.73e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.47e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.09e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.12e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.10e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.12e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.12e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.11.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.11.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.66e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.00e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.25e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.29e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.90e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.20e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.12.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.12.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.34e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.53e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.20e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.16e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.24e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.74e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.24e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.56e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.13.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.13.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.60e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.05e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.68e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.28e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.30e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.28e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.35e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.71e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.14.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.14.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.12e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.83e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.49e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.39e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.02e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.88e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.66e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.56e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.66e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.25e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.15.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.15.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.37e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.52e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.61e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.28e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.38e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.79e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.53e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.79e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.22e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.52e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.16.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.16.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.24e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.80e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.98e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.39e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.98e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.04e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.04e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.40e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.04e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.17.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.17.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.21e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.21e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.43e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.46e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.60e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.46e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.25e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.18.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.18.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.58e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.93e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.43e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.75e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.30e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.62e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.65e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.15e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.65e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.19.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.19.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.04e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.72e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.24e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.93e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.90e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.58e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.90e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.34e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.85e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.20.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.20.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.46e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.14e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.96e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.32e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.51e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.70e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.51e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.78e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.21.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.21.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.35e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.12e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.98e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.52e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.98e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.44e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.14e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.22.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.22.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.12e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.81e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.95e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.84e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.11e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=2.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=2.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.62e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.35e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.62e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.15e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.85e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.23.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.23.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.98e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.96e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.12e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.29e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.52e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.24.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.24.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.27e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.15e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.40e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.81e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.89e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.44e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.49e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.25.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.25.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.31e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.95e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.89e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.93e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.69e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.85e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.26.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.26.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.64e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.30e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.81e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.81e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.17e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.86e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=2.18e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=2.79e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.78e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.89e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.27.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.27.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.39e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.52e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.32e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.34e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.16e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.16e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.58e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.15e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.28.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.28.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.98e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.84e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.66e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.37e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.29.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.29.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.79e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.55e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.94e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.62e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.62e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.26e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.30.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.30.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.80e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.22e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.26e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.20e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.34e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.02e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=2.31e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=4.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.35e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.49e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.28e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.31.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.31.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.72e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.97e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.32e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.16e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.15e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.55e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.15e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.78e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.32.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.32.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.51e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.19e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.03e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.44e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.24e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.77e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.01e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.33.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.33.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.40e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.61e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.69e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.30e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.55e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.69e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.34e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.34.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.34.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.74e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.30e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.07e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.08e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.37e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.49e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.99e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=3.85e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.28e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.26e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.28e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.40e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.32e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.35.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.35.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.80e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.05e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.77e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.65e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.28e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.36.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.36.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.54e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.90e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.94e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.77e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.64e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.21e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.37.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.37.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.89e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.03e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.97e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.79e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.70e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.67e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.95e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.38.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.38.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.27e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.42e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.03e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.46e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=2.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=3.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.90e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.29e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.90e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.11e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.39.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.39.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.98e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.58e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.40e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.66e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.59e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.66e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.04e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.40.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.40.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.03e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.41e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.11e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.83e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.32e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.41.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.41.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.47e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.22e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.68e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.16e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.68e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.91e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.42.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.42.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.66e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.06e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.83e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.06e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.89e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.06e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.14e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.42e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.63e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=2.06e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=6.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.98e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.13e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.98e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.61e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.95e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.43.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.43.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.33e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.95e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.90e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.40e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.24e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.85e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.00e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.44.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.44.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.86e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.05e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.97e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.43e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.02e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.73e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.31e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.75e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.45.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.45.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.10e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.70e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.52e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.91e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.42e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.22e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.38e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.48e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.46.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.46.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.33e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.52e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.47e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.99e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.48e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=6.12e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.35e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.97e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.47.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.47.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.52e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.42e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.12e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.70e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.99e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.83e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.25e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.64e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.48.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.48.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.25e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.65e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.65e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.03e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.65e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.77e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.12e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.87e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.12e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.52e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.49.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.49.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.26e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.40e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.18e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.39e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.10e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.50.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.50.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.94e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.26e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.30e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.41e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.16e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.85e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=6.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.89e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.10e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.51.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.51.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.95e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.05e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.88e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.18e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.18e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.45e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.53e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.52.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.52.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.28e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.45e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.10e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.36e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.39e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.72e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.72e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.87e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.48e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.53.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.53.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.13e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.04e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.73e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.14e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.58e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.96e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.58e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.08e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.16e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.54.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.54.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.42e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.99e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.82e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.73e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.18e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.37e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.86e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=5.50e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.52e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.38e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.75e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.76e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.55.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.55.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.93e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.68e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.04e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.28e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.20e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.23e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.48e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.85e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.48e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.99e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.34e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.56.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.56.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.54e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.40e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.02e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.48e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.28e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.48e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.06e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.88e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.20e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.88e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.97e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.74e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.57.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.57.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.29e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.40e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.16e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.11e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.35e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.94e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.41e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.40e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.98e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.58.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.58.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.22e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.62e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.45e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.30e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.11e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.88e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.15e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.52e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.54e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.52e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.85e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.24e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.59.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.59.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.24e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.78e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.97e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.59e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.12e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.26e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.60e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.83e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.22e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.60.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.60.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.17e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.86e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.28e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.06e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.03e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.02e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.38e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.88e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.61.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.61.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.55e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.linear_attn.conv1d.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.conv1d.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.conv1d.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.out_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.70e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.linear_attn.out_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.out_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=9.77e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.linear_attn.in_proj_qkv.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.linear_attn.in_proj_qkv.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.in_proj_qkv.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.12e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.linear_attn.in_proj_z.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.80e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.linear_attn.in_proj_z.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.in_proj_z.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.50e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.linear_attn.in_proj_b.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.in_proj_b.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.in_proj_b.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.in_proj_a.input_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.in_proj_a.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.linear_attn.in_proj_a.weight_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=4.22e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.55e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.93e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.42e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.62.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.62.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.64e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.q_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.q_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.self_attn.q_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.39e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.k_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.k_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.self_attn.k_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.71e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.v_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=6.08e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.v_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.self_attn.v_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.02e+00 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.o_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=1.19e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.o_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.self_attn.o_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.93e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.q_bmm_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.self_attn.k_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.44e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.v_bmm_quantizer TensorQuantizer((4, 3) bit fake per-tensor amax=1.39e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.self_attn.softmax_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.mlp.gate_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.mlp.gate_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.mlp.gate_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=3.73e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.mlp.up_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.92e+01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.mlp.up_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.mlp.up_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=2.85e-01 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.mlp.down_proj.input_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=7.20e+02 calibrator=MaxCalibrator quant)
	model.language_model.layers.63.mlp.down_proj.output_quantizer TensorQuantizer(disabled)
	model.language_model.layers.63.mlp.down_proj.weight_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=5.00e-01 calibrator=MaxCalibrator quant)
	lm_head.input_quantizer TensorQuantizer(disabled)
	lm_head.output_quantizer TensorQuantizer(disabled)
	lm_head.weight_quantizer TensorQuantizer(disabled)
	2256 TensorQuantizers found in model