Instructions to use mconcat/Qwopus3.6-27B-v2-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mconcat/Qwopus3.6-27B-v2-AWQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="mconcat/Qwopus3.6-27B-v2-AWQ-4bit")
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("mconcat/Qwopus3.6-27B-v2-AWQ-4bit")
model = AutoModelForMultimodalLM.from_pretrained("mconcat/Qwopus3.6-27B-v2-AWQ-4bit", 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 mconcat/Qwopus3.6-27B-v2-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mconcat/Qwopus3.6-27B-v2-AWQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mconcat/Qwopus3.6-27B-v2-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mconcat/Qwopus3.6-27B-v2-AWQ-4bit

SGLang

How to use mconcat/Qwopus3.6-27B-v2-AWQ-4bit 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 "mconcat/Qwopus3.6-27B-v2-AWQ-4bit" \
    --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": "mconcat/Qwopus3.6-27B-v2-AWQ-4bit",
		"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 "mconcat/Qwopus3.6-27B-v2-AWQ-4bit" \
        --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": "mconcat/Qwopus3.6-27B-v2-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mconcat/Qwopus3.6-27B-v2-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/mconcat/Qwopus3.6-27B-v2-AWQ-4bit
```

Qwopus3.6-27B-v2-AWQ-4bit / quantization_config.json

mconcat

Fix: AWQ MTP 0% acceptance by adding mtp.* to modules_to_not_convert

baabcbb verified 6 months ago

Raw History Blame Contribute Delete

12.8 kB

{
  "bits": 4,
  "data_type": "int",
  "group_size": 128,
  "sym": false,
  "batch_size": 1,
  "low_gpu_mem_usage": true,
  "nsamples": 1024,
  "seqlen": 4096,
  "to_quant_block_names": "model.language_model.layers",
  "autoround_version": "0.12.3",
  "provider": "auto-round",
  "quant_method": "awq",
  "zero_point": true,
  "version": "gemm",
  "modules_to_not_convert": [
    "model.language_model.layers.34.linear_attn.in_proj_b",
    "model.language_model.layers.43.mlp.gate_proj",
    "model.language_model.layers.39.self_attn.o_proj",
    "model.language_model.layers.37.linear_attn.in_proj_a",
    "model.language_model.layers.34.linear_attn.out_proj",
    "model.language_model.layers.57.linear_attn.out_proj",
    "model.language_model.layers.19.mlp.down_proj",
    "model.language_model.layers.31.mlp.down_proj",
    "model.language_model.layers.0.linear_attn.in_proj_a",
    "model.language_model.layers.39.mlp.down_proj",
    "model.language_model.layers.60.linear_attn.out_proj",
    "model.language_model.layers.4.linear_attn.out_proj",
    "model.language_model.layers.13.linear_attn.in_proj_b",
    "model.language_model.layers.44.linear_attn.in_proj_a",
    "model.language_model.layers.21.linear_attn.in_proj_a",
    "model.language_model.layers.23.mlp.down_proj",
    "model.language_model.layers.51.mlp.up_proj",
    "model.language_model.layers.63.mlp.up_proj",
    "model.language_model.layers.5.linear_attn.out_proj",
    "model.language_model.layers.55.mlp.up_proj",
    "model.language_model.layers.36.linear_attn.in_proj_b",
    "model.visual.blocks",
    "model.language_model.layers.45.linear_attn.in_proj_b",
    "model.language_model.layers.55.mlp.down_proj",
    "model.language_model.layers.8.linear_attn.in_proj_a",
    "model.language_model.layers.12.linear_attn.in_proj_a",
    "model.language_model.layers.25.linear_attn.in_proj_a",
    "model.language_model.layers.46.linear_attn.in_proj_b",
    "model.language_model.layers.55.self_attn.q_proj",
    "model.language_model.layers.25.linear_attn.out_proj",
    "model.language_model.layers.18.linear_attn.in_proj_b",
    "model.language_model.layers.60.linear_attn.in_proj_b",
    "model.language_model.layers.40.linear_attn.out_proj",
    "model.language_model.layers.45.linear_attn.out_proj",
    "model.language_model.layers.30.linear_attn.out_proj",
    "model.language_model.layers.2.linear_attn.out_proj",
    "model.language_model.layers.20.linear_attn.in_proj_b",
    "model.language_model.layers.27.self_attn.o_proj",
    "model.language_model.layers.24.linear_attn.out_proj",
    "model.language_model.layers.62.linear_attn.out_proj",
    "model.language_model.layers.6.linear_attn.in_proj_a",
    "model.language_model.layers.53.linear_attn.in_proj_a",
    "model.language_model.layers.49.linear_attn.out_proj",
    "model.language_model.layers.43.mlp.up_proj",
    "model.language_model.layers.5.linear_attn.in_proj_b",
    "model.language_model.layers.29.linear_attn.out_proj",
    "model.language_model.layers.3.mlp.down_proj",
    "model.language_model.layers.0.linear_attn.in_proj_b",
    "model.language_model.layers.16.linear_attn.in_proj_a",
    "model.language_model.layers.29.linear_attn.in_proj_b",
    "model.language_model.layers.59.self_attn.o_proj",
    "model.language_model.layers.4.linear_attn.in_proj_a",
    "model.language_model.layers.32.linear_attn.out_proj",
    "model.language_model.layers.63.self_attn.o_proj",
    "visual",
    "linear_attn.out_proj",
    "model.language_model.layers.44.linear_attn.out_proj",
    "model.language_model.layers.44.linear_attn.in_proj_b",
    "model.language_model.layers.7.self_attn.o_proj",
    "model.language_model.layers.47.mlp.down_proj",
    "model.language_model.layers.49.linear_attn.in_proj_a",
    "model.language_model.layers.52.linear_attn.in_proj_a",
    "model.language_model.layers.12.linear_attn.out_proj",
    "model.language_model.layers.15.self_attn.o_proj",
    "model.language_model.layers.37.linear_attn.out_proj",
    "model.language_model.layers.41.linear_attn.in_proj_a",
    "model.language_model.layers.56.linear_attn.out_proj",
    "model.language_model.layers.51.self_attn.v_proj",
    "model.language_model.layers.47.self_attn.q_proj",
    "model.language_model.layers.37.linear_attn.in_proj_b",
    "model.language_model.layers.40.linear_attn.in_proj_a",
    "model.language_model.layers.20.linear_attn.out_proj",
    "model.language_model.layers.30.linear_attn.in_proj_a",
    "model.language_model.layers.28.linear_attn.in_proj_a",
    "model.language_model.layers.6.linear_attn.in_proj_b",
    "model.language_model.layers.13.linear_attn.in_proj_a",
    "model.language_model.layers.43.self_attn.o_proj",
    "model.language_model.layers.32.linear_attn.in_proj_b",
    "model.language_model.layers.46.linear_attn.out_proj",
    "model.language_model.layers.51.self_attn.k_proj",
    "model.language_model.layers.58.linear_attn.in_proj_b",
    "model.language_model.layers.9.linear_attn.in_proj_b",
    "model.language_model.layers.47.self_attn.k_proj",
    "model.language_model.layers.10.linear_attn.out_proj",
    "model.language_model.layers.49.linear_attn.in_proj_b",
    "model.language_model.layers.35.mlp.down_proj",
    "model.language_model.layers.10.linear_attn.in_proj_a",
    "model.language_model.layers.63.mlp.down_proj",
    "model.language_model.layers.60.linear_attn.in_proj_a",
    "model.language_model.layers.58.linear_attn.in_proj_a",
    "model.language_model.layers.18.linear_attn.out_proj",
    "model.language_model.layers.13.linear_attn.out_proj",
    "model.language_model.layers.55.mlp.gate_proj",
    "model.language_model.layers.53.linear_attn.in_proj_b",
    "model.language_model.layers.55.self_attn.o_proj",
    "model.language_model.layers.62.linear_attn.in_proj_a",
    "linear_attn.in_proj_b",
    "lm_head",
    "model.language_model.layers.50.linear_attn.in_proj_b",
    "model.language_model.layers.59.self_attn.q_proj",
    "model.language_model.layers.25.linear_attn.in_proj_b",
    "model.language_model.layers.22.linear_attn.out_proj",
    "model.language_model.layers.14.linear_attn.out_proj",
    "model.language_model.layers.15.mlp.down_proj",
    "model.language_model.layers.36.linear_attn.in_proj_a",
    "model.language_model.layers.38.linear_attn.in_proj_b",
    "model.language_model.layers.61.linear_attn.in_proj_b",
    "model.language_model.layers.14.linear_attn.in_proj_b",
    "model.language_model.layers.51.mlp.down_proj",
    "model.language_model.layers.42.linear_attn.out_proj",
    "model.language_model.layers.33.linear_attn.in_proj_a",
    "model.language_model.layers.54.linear_attn.in_proj_a",
    "model.language_model.layers.7.mlp.down_proj",
    "model.language_model.layers.54.linear_attn.in_proj_b",
    "linear_attn.in_proj_a",
    "model.language_model.layers.2.linear_attn.in_proj_a",
    "model.language_model.layers.29.linear_attn.in_proj_a",
    "model.language_model.layers.19.self_attn.o_proj",
    "model.language_model.layers.42.linear_attn.in_proj_b",
    "model.language_model.layers.38.linear_attn.in_proj_a",
    "model.language_model.layers.47.self_attn.o_proj",
    "model.language_model.layers.26.linear_attn.in_proj_b",
    "model.language_model.layers.5.linear_attn.in_proj_a",
    "model.language_model.layers.59.mlp.down_proj",
    "model.language_model.layers.43.self_attn.q_proj",
    "model.language_model.layers.0.linear_attn.out_proj",
    "model.language_model.layers.43.self_attn.k_proj",
    "model.language_model.layers.47.self_attn.v_proj",
    "model.language_model.layers.47.mlp.gate_proj",
    "model.language_model.layers.41.linear_attn.out_proj",
    "model.language_model.layers.31.self_attn.o_proj",
    "model.language_model.layers.22.linear_attn.in_proj_a",
    "model.language_model.layers.12.linear_attn.in_proj_b",
    "model.language_model.layers.34.linear_attn.in_proj_a",
    "model.language_model.layers.47.mlp.up_proj",
    "model.language_model.layers.48.linear_attn.out_proj",
    "model.language_model.layers.59.self_attn.v_proj",
    "model.language_model.layers.50.linear_attn.in_proj_a",
    "model.language_model.layers.16.linear_attn.out_proj",
    "model.language_model.layers.52.linear_attn.out_proj",
    "model.language_model.layers.48.linear_attn.in_proj_a",
    "model.language_model.layers.28.linear_attn.out_proj",
    "model.language_model.layers.41.linear_attn.in_proj_b",
    "model.language_model.layers.48.linear_attn.in_proj_b",
    "model.language_model.layers.3.self_attn.o_proj",
    "model.language_model.layers.11.mlp.down_proj",
    "model.language_model.layers.43.self_attn.v_proj",
    "model.language_model.layers.40.linear_attn.in_proj_b",
    "model.language_model.layers.23.self_attn.o_proj",
    "model.language_model.layers.63.self_attn.k_proj",
    "model.language_model.layers.26.linear_attn.out_proj",
    "model.language_model.layers.1.linear_attn.in_proj_b",
    "model.language_model.layers.53.linear_attn.out_proj",
    "model.language_model.layers.30.linear_attn.in_proj_b",
    "model.language_model.layers.59.mlp.gate_proj",
    "model.language_model.layers.51.mlp.gate_proj",
    "model.language_model.layers.8.linear_attn.out_proj",
    "model.language_model.layers.16.linear_attn.in_proj_b",
    "model.language_model.layers.61.linear_attn.in_proj_a",
    "model.language_model.layers.27.mlp.down_proj",
    "model.language_model.layers.58.linear_attn.out_proj",
    "model.language_model.layers.2.linear_attn.in_proj_b",
    "model.language_model.layers.24.linear_attn.in_proj_a",
    "model.language_model.layers.24.linear_attn.in_proj_b",
    "embed_tokens",
    "model.language_model.layers.33.linear_attn.in_proj_b",
    "self_attn.o_proj",
    "model.language_model.layers.57.linear_attn.in_proj_b",
    "model.language_model.layers.51.self_attn.o_proj",
    "model.language_model.layers.50.linear_attn.out_proj",
    "model.language_model.layers.45.linear_attn.in_proj_a",
    "model.language_model.layers.42.linear_attn.in_proj_a",
    "model.language_model.layers.1.linear_attn.in_proj_a",
    "model.language_model.layers.54.linear_attn.out_proj",
    "model.language_model.layers.21.linear_attn.out_proj",
    "model.language_model.layers.62.linear_attn.in_proj_b",
    "model.language_model.layers.56.linear_attn.in_proj_a",
    "model.language_model.layers.63.mlp.gate_proj",
    "model.language_model.layers.43.mlp.down_proj",
    "model.language_model.layers.59.self_attn.k_proj",
    "model.language_model.layers.11.self_attn.o_proj",
    "model.language_model.layers.6.linear_attn.out_proj",
    "model.language_model.layers.55.self_attn.k_proj",
    "model.language_model.layers.59.mlp.up_proj",
    "model.visual.merger.linear_fc2",
    "model.language_model.layers.33.linear_attn.out_proj",
    "model.language_model.layers.46.linear_attn.in_proj_a",
    "model.language_model.layers.14.linear_attn.in_proj_a",
    "model.language_model.layers.55.self_attn.v_proj",
    "model.language_model.layers.57.linear_attn.in_proj_a",
    "model.language_model.layers.10.linear_attn.in_proj_b",
    "model.language_model.layers.9.linear_attn.in_proj_a",
    "model.language_model.layers.1.linear_attn.out_proj",
    "model.language_model.layers.20.linear_attn.in_proj_a",
    "model.language_model.layers.17.linear_attn.out_proj",
    "model.language_model.layers.36.linear_attn.out_proj",
    "model.language_model.layers.17.linear_attn.in_proj_a",
    "model.language_model.layers.61.linear_attn.out_proj",
    "model.language_model.layers.18.linear_attn.in_proj_a",
    "model.language_model.layers.28.linear_attn.in_proj_b",
    "model.language_model.layers.35.self_attn.o_proj",
    "model.language_model.layers.38.linear_attn.out_proj",
    "model.language_model.layers.63.self_attn.q_proj",
    "model.language_model.layers.22.linear_attn.in_proj_b",
    "model.language_model.layers.9.linear_attn.out_proj",
    "model.language_model.layers.8.linear_attn.in_proj_b",
    "model.language_model.layers.52.linear_attn.in_proj_b",
    "model.language_model.layers.21.linear_attn.in_proj_b",
    "model.language_model.layers.4.linear_attn.in_proj_b",
    "model.language_model.layers.51.self_attn.q_proj",
    "model.language_model.layers.63.self_attn.v_proj",
    "model.language_model.layers.17.linear_attn.in_proj_b",
    "model.language_model.layers.26.linear_attn.in_proj_a",
    "model.language_model.layers.32.linear_attn.in_proj_a",
    "model.language_model.layers.56.linear_attn.in_proj_b",
    "model.visual.merger.linear_fc1",
    "mtp",
    "mtp.fc",
    "mtp.layers.0.self_attn.q_proj",
    "mtp.layers.0.self_attn.k_proj",
    "mtp.layers.0.self_attn.v_proj",
    "mtp.layers.0.self_attn.o_proj",
    "mtp.layers.0.mlp.gate_proj",
    "mtp.layers.0.mlp.up_proj",
    "mtp.layers.0.mlp.down_proj"
  ]
}

	{
	"bits": 4,
	"data_type": "int",
	"group_size": 128,
	"sym": false,
	"batch_size": 1,
	"low_gpu_mem_usage": true,
	"nsamples": 1024,
	"seqlen": 4096,
	"to_quant_block_names": "model.language_model.layers",
	"autoround_version": "0.12.3",
	"provider": "auto-round",
	"quant_method": "awq",
	"zero_point": true,
	"version": "gemm",
	"modules_to_not_convert": [
	"model.language_model.layers.34.linear_attn.in_proj_b",
	"model.language_model.layers.43.mlp.gate_proj",
	"model.language_model.layers.39.self_attn.o_proj",
	"model.language_model.layers.37.linear_attn.in_proj_a",
	"model.language_model.layers.34.linear_attn.out_proj",
	"model.language_model.layers.57.linear_attn.out_proj",
	"model.language_model.layers.19.mlp.down_proj",
	"model.language_model.layers.31.mlp.down_proj",
	"model.language_model.layers.0.linear_attn.in_proj_a",
	"model.language_model.layers.39.mlp.down_proj",
	"model.language_model.layers.60.linear_attn.out_proj",
	"model.language_model.layers.4.linear_attn.out_proj",
	"model.language_model.layers.13.linear_attn.in_proj_b",
	"model.language_model.layers.44.linear_attn.in_proj_a",
	"model.language_model.layers.21.linear_attn.in_proj_a",
	"model.language_model.layers.23.mlp.down_proj",
	"model.language_model.layers.51.mlp.up_proj",
	"model.language_model.layers.63.mlp.up_proj",
	"model.language_model.layers.5.linear_attn.out_proj",
	"model.language_model.layers.55.mlp.up_proj",
	"model.language_model.layers.36.linear_attn.in_proj_b",
	"model.visual.blocks",
	"model.language_model.layers.45.linear_attn.in_proj_b",
	"model.language_model.layers.55.mlp.down_proj",
	"model.language_model.layers.8.linear_attn.in_proj_a",
	"model.language_model.layers.12.linear_attn.in_proj_a",
	"model.language_model.layers.25.linear_attn.in_proj_a",
	"model.language_model.layers.46.linear_attn.in_proj_b",
	"model.language_model.layers.55.self_attn.q_proj",
	"model.language_model.layers.25.linear_attn.out_proj",
	"model.language_model.layers.18.linear_attn.in_proj_b",
	"model.language_model.layers.60.linear_attn.in_proj_b",
	"model.language_model.layers.40.linear_attn.out_proj",
	"model.language_model.layers.45.linear_attn.out_proj",
	"model.language_model.layers.30.linear_attn.out_proj",
	"model.language_model.layers.2.linear_attn.out_proj",
	"model.language_model.layers.20.linear_attn.in_proj_b",
	"model.language_model.layers.27.self_attn.o_proj",
	"model.language_model.layers.24.linear_attn.out_proj",
	"model.language_model.layers.62.linear_attn.out_proj",
	"model.language_model.layers.6.linear_attn.in_proj_a",
	"model.language_model.layers.53.linear_attn.in_proj_a",
	"model.language_model.layers.49.linear_attn.out_proj",
	"model.language_model.layers.43.mlp.up_proj",
	"model.language_model.layers.5.linear_attn.in_proj_b",
	"model.language_model.layers.29.linear_attn.out_proj",
	"model.language_model.layers.3.mlp.down_proj",
	"model.language_model.layers.0.linear_attn.in_proj_b",
	"model.language_model.layers.16.linear_attn.in_proj_a",
	"model.language_model.layers.29.linear_attn.in_proj_b",
	"model.language_model.layers.59.self_attn.o_proj",
	"model.language_model.layers.4.linear_attn.in_proj_a",
	"model.language_model.layers.32.linear_attn.out_proj",
	"model.language_model.layers.63.self_attn.o_proj",
	"visual",
	"linear_attn.out_proj",
	"model.language_model.layers.44.linear_attn.out_proj",
	"model.language_model.layers.44.linear_attn.in_proj_b",
	"model.language_model.layers.7.self_attn.o_proj",
	"model.language_model.layers.47.mlp.down_proj",
	"model.language_model.layers.49.linear_attn.in_proj_a",
	"model.language_model.layers.52.linear_attn.in_proj_a",
	"model.language_model.layers.12.linear_attn.out_proj",
	"model.language_model.layers.15.self_attn.o_proj",
	"model.language_model.layers.37.linear_attn.out_proj",
	"model.language_model.layers.41.linear_attn.in_proj_a",
	"model.language_model.layers.56.linear_attn.out_proj",
	"model.language_model.layers.51.self_attn.v_proj",
	"model.language_model.layers.47.self_attn.q_proj",
	"model.language_model.layers.37.linear_attn.in_proj_b",
	"model.language_model.layers.40.linear_attn.in_proj_a",
	"model.language_model.layers.20.linear_attn.out_proj",
	"model.language_model.layers.30.linear_attn.in_proj_a",
	"model.language_model.layers.28.linear_attn.in_proj_a",
	"model.language_model.layers.6.linear_attn.in_proj_b",
	"model.language_model.layers.13.linear_attn.in_proj_a",
	"model.language_model.layers.43.self_attn.o_proj",
	"model.language_model.layers.32.linear_attn.in_proj_b",
	"model.language_model.layers.46.linear_attn.out_proj",
	"model.language_model.layers.51.self_attn.k_proj",
	"model.language_model.layers.58.linear_attn.in_proj_b",
	"model.language_model.layers.9.linear_attn.in_proj_b",
	"model.language_model.layers.47.self_attn.k_proj",
	"model.language_model.layers.10.linear_attn.out_proj",
	"model.language_model.layers.49.linear_attn.in_proj_b",
	"model.language_model.layers.35.mlp.down_proj",
	"model.language_model.layers.10.linear_attn.in_proj_a",
	"model.language_model.layers.63.mlp.down_proj",
	"model.language_model.layers.60.linear_attn.in_proj_a",
	"model.language_model.layers.58.linear_attn.in_proj_a",
	"model.language_model.layers.18.linear_attn.out_proj",
	"model.language_model.layers.13.linear_attn.out_proj",
	"model.language_model.layers.55.mlp.gate_proj",
	"model.language_model.layers.53.linear_attn.in_proj_b",
	"model.language_model.layers.55.self_attn.o_proj",
	"model.language_model.layers.62.linear_attn.in_proj_a",
	"linear_attn.in_proj_b",
	"lm_head",
	"model.language_model.layers.50.linear_attn.in_proj_b",
	"model.language_model.layers.59.self_attn.q_proj",
	"model.language_model.layers.25.linear_attn.in_proj_b",
	"model.language_model.layers.22.linear_attn.out_proj",
	"model.language_model.layers.14.linear_attn.out_proj",
	"model.language_model.layers.15.mlp.down_proj",
	"model.language_model.layers.36.linear_attn.in_proj_a",
	"model.language_model.layers.38.linear_attn.in_proj_b",
	"model.language_model.layers.61.linear_attn.in_proj_b",
	"model.language_model.layers.14.linear_attn.in_proj_b",
	"model.language_model.layers.51.mlp.down_proj",
	"model.language_model.layers.42.linear_attn.out_proj",
	"model.language_model.layers.33.linear_attn.in_proj_a",
	"model.language_model.layers.54.linear_attn.in_proj_a",
	"model.language_model.layers.7.mlp.down_proj",
	"model.language_model.layers.54.linear_attn.in_proj_b",
	"linear_attn.in_proj_a",
	"model.language_model.layers.2.linear_attn.in_proj_a",
	"model.language_model.layers.29.linear_attn.in_proj_a",
	"model.language_model.layers.19.self_attn.o_proj",
	"model.language_model.layers.42.linear_attn.in_proj_b",
	"model.language_model.layers.38.linear_attn.in_proj_a",
	"model.language_model.layers.47.self_attn.o_proj",
	"model.language_model.layers.26.linear_attn.in_proj_b",
	"model.language_model.layers.5.linear_attn.in_proj_a",
	"model.language_model.layers.59.mlp.down_proj",
	"model.language_model.layers.43.self_attn.q_proj",
	"model.language_model.layers.0.linear_attn.out_proj",
	"model.language_model.layers.43.self_attn.k_proj",
	"model.language_model.layers.47.self_attn.v_proj",
	"model.language_model.layers.47.mlp.gate_proj",
	"model.language_model.layers.41.linear_attn.out_proj",
	"model.language_model.layers.31.self_attn.o_proj",
	"model.language_model.layers.22.linear_attn.in_proj_a",
	"model.language_model.layers.12.linear_attn.in_proj_b",
	"model.language_model.layers.34.linear_attn.in_proj_a",
	"model.language_model.layers.47.mlp.up_proj",
	"model.language_model.layers.48.linear_attn.out_proj",
	"model.language_model.layers.59.self_attn.v_proj",
	"model.language_model.layers.50.linear_attn.in_proj_a",
	"model.language_model.layers.16.linear_attn.out_proj",
	"model.language_model.layers.52.linear_attn.out_proj",
	"model.language_model.layers.48.linear_attn.in_proj_a",
	"model.language_model.layers.28.linear_attn.out_proj",
	"model.language_model.layers.41.linear_attn.in_proj_b",
	"model.language_model.layers.48.linear_attn.in_proj_b",
	"model.language_model.layers.3.self_attn.o_proj",
	"model.language_model.layers.11.mlp.down_proj",
	"model.language_model.layers.43.self_attn.v_proj",
	"model.language_model.layers.40.linear_attn.in_proj_b",
	"model.language_model.layers.23.self_attn.o_proj",
	"model.language_model.layers.63.self_attn.k_proj",
	"model.language_model.layers.26.linear_attn.out_proj",
	"model.language_model.layers.1.linear_attn.in_proj_b",
	"model.language_model.layers.53.linear_attn.out_proj",
	"model.language_model.layers.30.linear_attn.in_proj_b",
	"model.language_model.layers.59.mlp.gate_proj",
	"model.language_model.layers.51.mlp.gate_proj",
	"model.language_model.layers.8.linear_attn.out_proj",
	"model.language_model.layers.16.linear_attn.in_proj_b",
	"model.language_model.layers.61.linear_attn.in_proj_a",
	"model.language_model.layers.27.mlp.down_proj",
	"model.language_model.layers.58.linear_attn.out_proj",
	"model.language_model.layers.2.linear_attn.in_proj_b",
	"model.language_model.layers.24.linear_attn.in_proj_a",
	"model.language_model.layers.24.linear_attn.in_proj_b",
	"embed_tokens",
	"model.language_model.layers.33.linear_attn.in_proj_b",
	"self_attn.o_proj",
	"model.language_model.layers.57.linear_attn.in_proj_b",
	"model.language_model.layers.51.self_attn.o_proj",
	"model.language_model.layers.50.linear_attn.out_proj",
	"model.language_model.layers.45.linear_attn.in_proj_a",
	"model.language_model.layers.42.linear_attn.in_proj_a",
	"model.language_model.layers.1.linear_attn.in_proj_a",
	"model.language_model.layers.54.linear_attn.out_proj",
	"model.language_model.layers.21.linear_attn.out_proj",
	"model.language_model.layers.62.linear_attn.in_proj_b",
	"model.language_model.layers.56.linear_attn.in_proj_a",
	"model.language_model.layers.63.mlp.gate_proj",
	"model.language_model.layers.43.mlp.down_proj",
	"model.language_model.layers.59.self_attn.k_proj",
	"model.language_model.layers.11.self_attn.o_proj",
	"model.language_model.layers.6.linear_attn.out_proj",
	"model.language_model.layers.55.self_attn.k_proj",
	"model.language_model.layers.59.mlp.up_proj",
	"model.visual.merger.linear_fc2",
	"model.language_model.layers.33.linear_attn.out_proj",
	"model.language_model.layers.46.linear_attn.in_proj_a",
	"model.language_model.layers.14.linear_attn.in_proj_a",
	"model.language_model.layers.55.self_attn.v_proj",
	"model.language_model.layers.57.linear_attn.in_proj_a",
	"model.language_model.layers.10.linear_attn.in_proj_b",
	"model.language_model.layers.9.linear_attn.in_proj_a",
	"model.language_model.layers.1.linear_attn.out_proj",
	"model.language_model.layers.20.linear_attn.in_proj_a",
	"model.language_model.layers.17.linear_attn.out_proj",
	"model.language_model.layers.36.linear_attn.out_proj",
	"model.language_model.layers.17.linear_attn.in_proj_a",
	"model.language_model.layers.61.linear_attn.out_proj",
	"model.language_model.layers.18.linear_attn.in_proj_a",
	"model.language_model.layers.28.linear_attn.in_proj_b",
	"model.language_model.layers.35.self_attn.o_proj",
	"model.language_model.layers.38.linear_attn.out_proj",
	"model.language_model.layers.63.self_attn.q_proj",
	"model.language_model.layers.22.linear_attn.in_proj_b",
	"model.language_model.layers.9.linear_attn.out_proj",
	"model.language_model.layers.8.linear_attn.in_proj_b",
	"model.language_model.layers.52.linear_attn.in_proj_b",
	"model.language_model.layers.21.linear_attn.in_proj_b",
	"model.language_model.layers.4.linear_attn.in_proj_b",
	"model.language_model.layers.51.self_attn.q_proj",
	"model.language_model.layers.63.self_attn.v_proj",
	"model.language_model.layers.17.linear_attn.in_proj_b",
	"model.language_model.layers.26.linear_attn.in_proj_a",
	"model.language_model.layers.32.linear_attn.in_proj_a",
	"model.language_model.layers.56.linear_attn.in_proj_b",
	"model.visual.merger.linear_fc1",
	"mtp",
	"mtp.fc",
	"mtp.layers.0.self_attn.q_proj",
	"mtp.layers.0.self_attn.k_proj",
	"mtp.layers.0.self_attn.v_proj",
	"mtp.layers.0.self_attn.o_proj",
	"mtp.layers.0.mlp.gate_proj",
	"mtp.layers.0.mlp.up_proj",
	"mtp.layers.0.mlp.down_proj"
	]
	}