Instructions to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with Transformers:

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

pipe = pipeline("text-generation", model="dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf")
model = AutoModelForCausalLM.from_pretrained("dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf

SGLang

How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf 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 "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf" \
    --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": "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf",
		"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 "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf" \
        --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": "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with Docker Model Runner:
```
docker model run hf.co/dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf
```

dbw6 commited on Apr 6

Commit

00b90c1

verified ·

1 Parent(s): 33c8bae

Upload AQLM HF export

Browse files

Files changed (4) hide show

config.json +0 -6
model-00001-of-00002.safetensors +2 -2
model-00002-of-00002.safetensors +2 -2
model.safetensors.index.json +79 -67

config.json CHANGED Viewed

@@ -155,9 +155,6 @@
       "model.layers.25.self_attn.q_norm.weight",
       "model.layers.25.self_attn.k_norm.weight",
       "model.layers.25.mlp.gate.weight",
-      "model.layers.25.mlp.experts.64.gate_proj.weight",
-      "model.layers.25.mlp.experts.64.up_proj.weight",
-      "model.layers.25.mlp.experts.64.down_proj.weight",
       "model.layers.25.input_layernorm.weight",
       "model.layers.25.post_attention_layernorm.weight",
       "model.layers.26.self_attn.q_norm.weight",
@@ -218,9 +215,6 @@
       "model.layers.37.self_attn.q_norm.weight",
       "model.layers.37.self_attn.k_norm.weight",
       "model.layers.37.mlp.gate.weight",
-      "model.layers.37.mlp.experts.64.gate_proj.weight",
-      "model.layers.37.mlp.experts.64.up_proj.weight",
-      "model.layers.37.mlp.experts.64.down_proj.weight",
       "model.layers.37.input_layernorm.weight",
       "model.layers.37.post_attention_layernorm.weight",
       "model.layers.38.self_attn.q_norm.weight",

       "model.layers.25.self_attn.q_norm.weight",
       "model.layers.25.self_attn.k_norm.weight",
       "model.layers.25.mlp.gate.weight",
       "model.layers.25.input_layernorm.weight",
       "model.layers.25.post_attention_layernorm.weight",
       "model.layers.26.self_attn.q_norm.weight",
       "model.layers.37.self_attn.q_norm.weight",
       "model.layers.37.self_attn.k_norm.weight",
       "model.layers.37.mlp.gate.weight",
       "model.layers.37.input_layernorm.weight",
       "model.layers.37.post_attention_layernorm.weight",
       "model.layers.38.self_attn.q_norm.weight",

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ebd9bc161f6e34a8a5c5ffca6bb9c1ac99708d0208e41a32fbfe26a222b57a
-size 5003727864

 version https://git-lfs.github.com/spec/v1
+oid sha256:80eacb7129a3e5dc31c2781582a8f98be9ee8ddc32500f66527a316363c18bd6
+size 5003586984

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab0bc92acb77b12d6dd3ce7715e46efd227e6f24a9709449a544ef39a0b35c2
-size 3961428800

 version https://git-lfs.github.com/spec/v1
+oid sha256:35d469823f5d2114f6c751ae8052eaae3294fe3984d7e4eeea7ad527c14c2688
+size 3945119504

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8958244864
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -21849,9 +21849,15 @@
     "model.layers.25.mlp.experts.63.up_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.63.up_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.63.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.experts.64.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.experts.64.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.65.down_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.65.down_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.65.down_proj.scales": "model-00001-of-00002.safetensors",
@@ -23821,24 +23827,24 @@
     "model.layers.27.mlp.experts.27.up_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.27.up_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.27.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.experts.28.down_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.28.down_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.28.down_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.gate_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.gate_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.gate_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.up_proj.codebooks": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.experts.28.up_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.28.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.down_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.down_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.gate_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.gate_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.up_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.up_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.29.up_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.down_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.down_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.down_proj.scales": "model-00001-of-00002.safetensors",
@@ -23848,55 +23854,55 @@
     "model.layers.27.mlp.experts.3.up_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.up_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.up_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.down_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.down_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.gate_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.gate_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.up_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.up_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.30.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.down_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.down_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.gate_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.gate_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.up_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.up_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.31.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.down_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.down_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.gate_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.gate_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.up_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.up_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.32.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.down_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.down_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.gate_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.gate_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.up_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.up_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.33.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.down_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.down_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.gate_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.gate_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.up_proj.codebooks": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.up_proj.codes": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.34.up_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.down_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.down_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.experts.35.gate_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.gate_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.gate_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.up_proj.codebooks": "model-00002-of-00002.safetensors",
@@ -37040,9 +37046,15 @@
     "model.layers.37.mlp.experts.63.up_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.63.up_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.63.up_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.37.mlp.experts.64.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.37.mlp.experts.64.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.65.down_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.65.down_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.65.down_proj.scales": "model-00002-of-00002.safetensors",

 {
   "metadata": {
+    "total_size": 8941793280
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.experts.63.up_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.63.up_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.63.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.gate_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.gate_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.experts.64.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.65.down_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.65.down_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.experts.65.down_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.27.up_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.27.up_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.27.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.28.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.28.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.28.down_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.gate_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.gate_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.gate_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.28.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.28.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.28.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.gate_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.gate_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.29.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.down_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.down_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.down_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.up_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.up_proj.codes": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.3.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.gate_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.gate_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.30.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.gate_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.gate_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.31.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.gate_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.gate_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.32.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.gate_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.gate_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.33.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.down_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.down_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.gate_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.gate_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.up_proj.codebooks": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.up_proj.codes": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.experts.34.up_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.down_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.down_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.experts.35.gate_proj.codebooks": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.gate_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.gate_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.experts.35.up_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.63.up_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.63.up_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.63.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.down_proj.codebooks": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.down_proj.codes": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.gate_proj.codebooks": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.gate_proj.codes": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.up_proj.codebooks": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.up_proj.codes": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.experts.64.up_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.65.down_proj.codebooks": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.65.down_proj.codes": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.experts.65.down_proj.scales": "model-00002-of-00002.safetensors",