Instructions to use YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound with Transformers:

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

pipe = pipeline("text-generation", model="YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound")
model = AutoModelForMultimodalLM.from_pretrained("YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound

SGLang

How to use YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound 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 "YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound" \
    --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": "YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound",
		"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 "YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound" \
        --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": "YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound with Docker Model Runner:
```
docker model run hf.co/YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound
```

YuYu1015 commited on Apr 12

Commit

5b45609

verified ·

1 Parent(s): a70c48a

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -38

README.md CHANGED Viewed

@@ -129,25 +129,6 @@ vllm serve /path/to/model \
 - `--performance-mode interactivity` enables latency-optimized CUDA graphs and kernels
 - Clear page cache before starting on UMA: `sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'`
-### Reproduce Quantization
-**Environment:** `nvcr.io/nvidia/pytorch:26.03-py3` with `auto-round==0.12.2`
-```bash
-auto-round \
-    --model_name /path/to/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated \
-    --output_dir /path/to/output \
-    --bits 4 \
-    --group_size 128 \
-    --iters 200 \
-    --nsamples 512 \
-    --seqlen 2048 \
-    --format auto_round \
-    --ignore_layers shared_expert,shared_expert_gate,mtp.fc,linear_attn
-```
-Quantization took approximately 4 hours on a single NVIDIA DGX Spark (GB10).
 ### Safety Warning
 This model has safety filtering removed (abliterated) and may generate inappropriate content. Users are solely responsible for all consequences arising from its use. Please ensure usage complies with local laws and ethical standards.
@@ -243,25 +224,6 @@ This model has safety filtering removed (abliterated) and may generate inappropr
 - `--performance-mode interactivity` 啟用延遲最佳化的 CUDA graphs 和 kernel
 - UMA 架構啟動前請先清除 page cache：`sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'`
-### 量化指令
-**環境：** `nvcr.io/nvidia/pytorch:26.03-py3` + `auto-round==0.12.2`
-```bash
-auto-round \
-    --model_name /path/to/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated \
-    --output_dir /path/to/output \
-    --bits 4 \
-    --group_size 128 \
-    --iters 200 \
-    --nsamples 512 \
-    --seqlen 2048 \
-    --format auto_round \
-    --ignore_layers shared_expert,shared_expert_gate,mtp.fc,linear_attn
-```
-在單台 NVIDIA DGX Spark (GB10) 上量化，耗時約 4 小時。
 ### 安全警告
 此模型已移除安全過濾機制（abliterated），可能產生敏感、爭議性或不當內容。使用者須自行承擔所有風險與法律責任，並確保使用方式符合當地法規與倫理標準。

 - `--performance-mode interactivity` enables latency-optimized CUDA graphs and kernels
 - Clear page cache before starting on UMA: `sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'`
 ### Safety Warning
 This model has safety filtering removed (abliterated) and may generate inappropriate content. Users are solely responsible for all consequences arising from its use. Please ensure usage complies with local laws and ethical standards.
 - `--performance-mode interactivity` 啟用延遲最佳化的 CUDA graphs 和 kernel
 - UMA 架構啟動前請先清除 page cache：`sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'`
 ### 安全警告
 此模型已移除安全過濾機制（abliterated），可能產生敏感、爭議性或不當內容。使用者須自行承擔所有風險與法律責任，並確保使用方式符合當地法規與倫理標準。