Instructions to use sahilchachra/LFM2.5-VL-3B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sahilchachra/LFM2.5-VL-3B-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="sahilchachra/LFM2.5-VL-3B-AWQ", trust_remote_code=True)
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("sahilchachra/LFM2.5-VL-3B-AWQ", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("sahilchachra/LFM2.5-VL-3B-AWQ", trust_remote_code=True, 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 sahilchachra/LFM2.5-VL-3B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sahilchachra/LFM2.5-VL-3B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sahilchachra/LFM2.5-VL-3B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/sahilchachra/LFM2.5-VL-3B-AWQ

SGLang

How to use sahilchachra/LFM2.5-VL-3B-AWQ 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 "sahilchachra/LFM2.5-VL-3B-AWQ" \
    --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": "sahilchachra/LFM2.5-VL-3B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "sahilchachra/LFM2.5-VL-3B-AWQ" \
        --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": "sahilchachra/LFM2.5-VL-3B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use sahilchachra/LFM2.5-VL-3B-AWQ with Docker Model Runner:
```
docker model run hf.co/sahilchachra/LFM2.5-VL-3B-AWQ
```

sahilchachra commited on Aug 21

Commit

9fe123d

verified ·

1 Parent(s): 5703ddf

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +4 -373

config.json CHANGED Viewed

@@ -82,379 +82,10 @@
     "format": "pack-quantized",
     "global_compression_ratio": null,
     "ignore": [
-      "model.vision_tower.embeddings.patch_embedding",
-      "model.vision_tower.vision_model.embeddings.patch_embedding",
-      "model.vision_tower.encoder.layers.0.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.0.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.0.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.0.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.0.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1",
-      "model.vision_tower.encoder.layers.0.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2",
-      "model.vision_tower.encoder.layers.1.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.1.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.1.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.1.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.1.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1",
-      "model.vision_tower.encoder.layers.1.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2",
-      "model.vision_tower.encoder.layers.2.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.2.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.2.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.2.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.2.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1",
-      "model.vision_tower.encoder.layers.2.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2",
-      "model.vision_tower.encoder.layers.3.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.3.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.3.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.3.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.3.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1",
-      "model.vision_tower.encoder.layers.3.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2",
-      "model.vision_tower.encoder.layers.4.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.4.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.4.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.4.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.4.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1",
-      "model.vision_tower.encoder.layers.4.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2",
-      "model.vision_tower.encoder.layers.5.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.5.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.5.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.5.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.5.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1",
-      "model.vision_tower.encoder.layers.5.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2",
-      "model.vision_tower.encoder.layers.6.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.6.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.6.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.6.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.6.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1",
-      "model.vision_tower.encoder.layers.6.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2",
-      "model.vision_tower.encoder.layers.7.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.7.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.7.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.7.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.7.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1",
-      "model.vision_tower.encoder.layers.7.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2",
-      "model.vision_tower.encoder.layers.8.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.8.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.8.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.8.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.8.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1",
-      "model.vision_tower.encoder.layers.8.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2",
-      "model.vision_tower.encoder.layers.9.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.9.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.9.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.9.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.9.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1",
-      "model.vision_tower.encoder.layers.9.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2",
-      "model.vision_tower.encoder.layers.10.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.10.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.10.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.10.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.10.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1",
-      "model.vision_tower.encoder.layers.10.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2",
-      "model.vision_tower.encoder.layers.11.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.11.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.11.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.11.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.11.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1",
-      "model.vision_tower.encoder.layers.11.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2",
-      "model.vision_tower.encoder.layers.12.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.12.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.12.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.12.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.12.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1",
-      "model.vision_tower.encoder.layers.12.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2",
-      "model.vision_tower.encoder.layers.13.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.13.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.13.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.13.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.13.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1",
-      "model.vision_tower.encoder.layers.13.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2",
-      "model.vision_tower.encoder.layers.14.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.14.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.14.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.14.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.14.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1",
-      "model.vision_tower.encoder.layers.14.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2",
-      "model.vision_tower.encoder.layers.15.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.15.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.15.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.15.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.15.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1",
-      "model.vision_tower.encoder.layers.15.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2",
-      "model.vision_tower.encoder.layers.16.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.16.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.16.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.16.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.16.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1",
-      "model.vision_tower.encoder.layers.16.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2",
-      "model.vision_tower.encoder.layers.17.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.17.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.17.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.17.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.17.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1",
-      "model.vision_tower.encoder.layers.17.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2",
-      "model.vision_tower.encoder.layers.18.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.18.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.18.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.18.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.18.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1",
-      "model.vision_tower.encoder.layers.18.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2",
-      "model.vision_tower.encoder.layers.19.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.19.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.19.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.19.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.19.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1",
-      "model.vision_tower.encoder.layers.19.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2",
-      "model.vision_tower.encoder.layers.20.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.20.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.20.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.20.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.20.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1",
-      "model.vision_tower.encoder.layers.20.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2",
-      "model.vision_tower.encoder.layers.21.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.21.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.21.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.21.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.21.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1",
-      "model.vision_tower.encoder.layers.21.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2",
-      "model.vision_tower.encoder.layers.22.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.22.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.22.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.22.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.22.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1",
-      "model.vision_tower.encoder.layers.22.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2",
-      "model.vision_tower.encoder.layers.23.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.23.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.23.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.23.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.23.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1",
-      "model.vision_tower.encoder.layers.23.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2",
-      "model.vision_tower.encoder.layers.24.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.24.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.24.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.24.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.24.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1",
-      "model.vision_tower.encoder.layers.24.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2",
-      "model.vision_tower.encoder.layers.25.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.25.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.25.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.25.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.25.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1",
-      "model.vision_tower.encoder.layers.25.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2",
-      "model.vision_tower.encoder.layers.26.self_attn.k_proj",
-      "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj",
-      "model.vision_tower.encoder.layers.26.self_attn.v_proj",
-      "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj",
-      "model.vision_tower.encoder.layers.26.self_attn.q_proj",
-      "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj",
-      "model.vision_tower.encoder.layers.26.self_attn.out_proj",
-      "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj",
-      "model.vision_tower.encoder.layers.26.mlp.fc1",
-      "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1",
-      "model.vision_tower.encoder.layers.26.mlp.fc2",
-      "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2",
-      "model.multi_modal_projector.linear_1",
-      "model.multi_modal_projector.linear_2",
-      "model.language_model.layers.0.conv.in_proj",
-      "model.language_model.layers.0.conv.out_proj",
-      "model.language_model.layers.1.conv.in_proj",
-      "model.language_model.layers.1.conv.out_proj",
-      "model.language_model.layers.3.conv.in_proj",
-      "model.language_model.layers.3.conv.out_proj",
-      "model.language_model.layers.4.conv.in_proj",
-      "model.language_model.layers.4.conv.out_proj",
-      "model.language_model.layers.6.conv.in_proj",
-      "model.language_model.layers.6.conv.out_proj",
-      "model.language_model.layers.7.conv.in_proj",
-      "model.language_model.layers.7.conv.out_proj",
-      "model.language_model.layers.8.conv.in_proj",
-      "model.language_model.layers.8.conv.out_proj",
-      "model.language_model.layers.10.conv.in_proj",
-      "model.language_model.layers.10.conv.out_proj",
-      "model.language_model.layers.11.conv.in_proj",
-      "model.language_model.layers.11.conv.out_proj",
-      "model.language_model.layers.12.conv.in_proj",
-      "model.language_model.layers.12.conv.out_proj",
-      "model.language_model.layers.14.conv.in_proj",
-      "model.language_model.layers.14.conv.out_proj",
-      "model.language_model.layers.15.conv.in_proj",
-      "model.language_model.layers.15.conv.out_proj",
-      "model.language_model.layers.16.conv.in_proj",
-      "model.language_model.layers.16.conv.out_proj",
-      "model.language_model.layers.18.conv.in_proj",
-      "model.language_model.layers.18.conv.out_proj",
-      "model.language_model.layers.19.conv.in_proj",
-      "model.language_model.layers.19.conv.out_proj",
-      "model.language_model.layers.20.conv.in_proj",
-      "model.language_model.layers.20.conv.out_proj",
-      "model.language_model.layers.22.conv.in_proj",
-      "model.language_model.layers.22.conv.out_proj",
-      "model.language_model.layers.23.conv.in_proj",
-      "model.language_model.layers.23.conv.out_proj",
-      "model.language_model.layers.25.conv.in_proj",
-      "model.language_model.layers.25.conv.out_proj",
-      "model.language_model.layers.26.conv.in_proj",
-      "model.language_model.layers.26.conv.out_proj",
-      "model.language_model.layers.28.conv.in_proj",
-      "model.language_model.layers.28.conv.out_proj",
-      "model.language_model.layers.29.conv.in_proj",
-      "model.language_model.layers.29.conv.out_proj",
-      "lm_head"
     ],
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",

     "format": "pack-quantized",
     "global_compression_ratio": null,
     "ignore": [
+      "re:.*lm_head",
+      "re:.*vision_tower\\..*",
+      "re:.*multi_modal_projector\\..*",
+      "re:.*layers\\.\\d+\\.(short_)?conv\\.(in|out)_proj"
     ],
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",