Instructions to use simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors with Transformers:

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

pipe = pipeline("image-text-to-text", model="simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors")
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("simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors")
model = AutoModelForMultimodalLM.from_pretrained("simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors", 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 simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors",
		"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/simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors

SGLang

How to use simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors 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 "simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors" \
    --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": "simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors",
		"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 "simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors" \
        --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": "simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors",
		"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 simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors with Docker Model Runner:
```
docker model run hf.co/simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors
```

Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors / recipe.yaml

florianvoss

Upload Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors

f3ae15f verified about 1 month ago

Raw

History Blame Contribute Delete

21 kB

	# Effective Qwen2.5-VL-3B quantization recipe
	# Calibration: lmms-lab/flickr30k test[:512], deterministic order
	text_gptq_int4_g256:
	method: GPTQ
	weights:
	num_bits: 4
	type: int
	symmetric: true
	strategy: group
	group_size: 256
	targets:
	- model.language_model.layers.0.self_attn.q_proj
	- model.language_model.layers.0.self_attn.k_proj
	- model.language_model.layers.0.self_attn.v_proj
	- model.language_model.layers.0.self_attn.o_proj
	- model.language_model.layers.0.mlp.gate_proj
	- model.language_model.layers.0.mlp.up_proj
	- model.language_model.layers.0.mlp.down_proj
	- model.language_model.layers.1.self_attn.q_proj
	- model.language_model.layers.1.self_attn.k_proj
	- model.language_model.layers.1.self_attn.v_proj
	- model.language_model.layers.1.self_attn.o_proj
	- model.language_model.layers.1.mlp.gate_proj
	- model.language_model.layers.1.mlp.up_proj
	- model.language_model.layers.1.mlp.down_proj
	- model.language_model.layers.2.self_attn.q_proj
	- model.language_model.layers.2.self_attn.k_proj
	- model.language_model.layers.2.self_attn.v_proj
	- model.language_model.layers.2.self_attn.o_proj
	- model.language_model.layers.2.mlp.gate_proj
	- model.language_model.layers.2.mlp.up_proj
	- model.language_model.layers.2.mlp.down_proj
	- model.language_model.layers.3.self_attn.q_proj
	- model.language_model.layers.3.self_attn.k_proj
	- model.language_model.layers.3.self_attn.v_proj
	- model.language_model.layers.3.self_attn.o_proj
	- model.language_model.layers.3.mlp.gate_proj
	- model.language_model.layers.3.mlp.up_proj
	- model.language_model.layers.3.mlp.down_proj
	- model.language_model.layers.4.self_attn.q_proj
	- model.language_model.layers.4.self_attn.k_proj
	- model.language_model.layers.4.self_attn.v_proj
	- model.language_model.layers.4.self_attn.o_proj
	- model.language_model.layers.4.mlp.gate_proj
	- model.language_model.layers.4.mlp.up_proj
	- model.language_model.layers.4.mlp.down_proj
	- model.language_model.layers.5.self_attn.q_proj
	- model.language_model.layers.5.self_attn.k_proj
	- model.language_model.layers.5.self_attn.v_proj
	- model.language_model.layers.5.self_attn.o_proj
	- model.language_model.layers.5.mlp.gate_proj
	- model.language_model.layers.5.mlp.up_proj
	- model.language_model.layers.5.mlp.down_proj
	- model.language_model.layers.6.self_attn.q_proj
	- model.language_model.layers.6.self_attn.k_proj
	- model.language_model.layers.6.self_attn.v_proj
	- model.language_model.layers.6.self_attn.o_proj
	- model.language_model.layers.6.mlp.gate_proj
	- model.language_model.layers.6.mlp.up_proj
	- model.language_model.layers.6.mlp.down_proj
	- model.language_model.layers.7.self_attn.q_proj
	- model.language_model.layers.7.self_attn.k_proj
	- model.language_model.layers.7.self_attn.v_proj
	- model.language_model.layers.7.self_attn.o_proj
	- model.language_model.layers.7.mlp.gate_proj
	- model.language_model.layers.7.mlp.up_proj
	- model.language_model.layers.7.mlp.down_proj
	- model.language_model.layers.8.self_attn.q_proj
	- model.language_model.layers.8.self_attn.k_proj
	- model.language_model.layers.8.self_attn.v_proj
	- model.language_model.layers.8.self_attn.o_proj
	- model.language_model.layers.8.mlp.gate_proj
	- model.language_model.layers.8.mlp.up_proj
	- model.language_model.layers.8.mlp.down_proj
	- model.language_model.layers.9.self_attn.q_proj
	- model.language_model.layers.9.self_attn.k_proj
	- model.language_model.layers.9.self_attn.v_proj
	- model.language_model.layers.9.self_attn.o_proj
	- model.language_model.layers.9.mlp.gate_proj
	- model.language_model.layers.9.mlp.up_proj
	- model.language_model.layers.9.mlp.down_proj
	- model.language_model.layers.10.self_attn.q_proj
	- model.language_model.layers.10.self_attn.k_proj
	- model.language_model.layers.10.self_attn.v_proj
	- model.language_model.layers.10.self_attn.o_proj
	- model.language_model.layers.10.mlp.gate_proj
	- model.language_model.layers.10.mlp.up_proj
	- model.language_model.layers.10.mlp.down_proj
	- model.language_model.layers.11.self_attn.q_proj
	- model.language_model.layers.11.self_attn.k_proj
	- model.language_model.layers.11.self_attn.v_proj
	- model.language_model.layers.11.self_attn.o_proj
	- model.language_model.layers.11.mlp.gate_proj
	- model.language_model.layers.11.mlp.up_proj
	- model.language_model.layers.11.mlp.down_proj
	- model.language_model.layers.12.self_attn.q_proj
	- model.language_model.layers.12.self_attn.k_proj
	- model.language_model.layers.12.self_attn.v_proj
	- model.language_model.layers.12.self_attn.o_proj
	- model.language_model.layers.12.mlp.gate_proj
	- model.language_model.layers.12.mlp.up_proj
	- model.language_model.layers.12.mlp.down_proj
	- model.language_model.layers.13.self_attn.q_proj
	- model.language_model.layers.13.self_attn.k_proj
	- model.language_model.layers.13.self_attn.v_proj
	- model.language_model.layers.13.self_attn.o_proj
	- model.language_model.layers.13.mlp.gate_proj
	- model.language_model.layers.13.mlp.up_proj
	- model.language_model.layers.13.mlp.down_proj
	- model.language_model.layers.14.self_attn.q_proj
	- model.language_model.layers.14.self_attn.k_proj
	- model.language_model.layers.14.self_attn.v_proj
	- model.language_model.layers.14.self_attn.o_proj
	- model.language_model.layers.14.mlp.gate_proj
	- model.language_model.layers.14.mlp.up_proj
	- model.language_model.layers.14.mlp.down_proj
	- model.language_model.layers.15.self_attn.q_proj
	- model.language_model.layers.15.self_attn.k_proj
	- model.language_model.layers.15.self_attn.v_proj
	- model.language_model.layers.15.self_attn.o_proj
	- model.language_model.layers.15.mlp.gate_proj
	- model.language_model.layers.15.mlp.up_proj
	- model.language_model.layers.15.mlp.down_proj
	- model.language_model.layers.16.self_attn.q_proj
	- model.language_model.layers.16.self_attn.k_proj
	- model.language_model.layers.16.self_attn.v_proj
	- model.language_model.layers.16.self_attn.o_proj
	- model.language_model.layers.16.mlp.gate_proj
	- model.language_model.layers.16.mlp.up_proj
	- model.language_model.layers.16.mlp.down_proj
	- model.language_model.layers.17.self_attn.q_proj
	- model.language_model.layers.17.self_attn.k_proj
	- model.language_model.layers.17.self_attn.v_proj
	- model.language_model.layers.17.self_attn.o_proj
	- model.language_model.layers.17.mlp.gate_proj
	- model.language_model.layers.17.mlp.up_proj
	- model.language_model.layers.17.mlp.down_proj
	- model.language_model.layers.18.self_attn.q_proj
	- model.language_model.layers.18.self_attn.k_proj
	- model.language_model.layers.18.self_attn.v_proj
	- model.language_model.layers.18.self_attn.o_proj
	- model.language_model.layers.18.mlp.gate_proj
	- model.language_model.layers.18.mlp.up_proj
	- model.language_model.layers.18.mlp.down_proj
	- model.language_model.layers.19.self_attn.q_proj
	- model.language_model.layers.19.self_attn.k_proj
	- model.language_model.layers.19.self_attn.v_proj
	- model.language_model.layers.19.self_attn.o_proj
	- model.language_model.layers.19.mlp.gate_proj
	- model.language_model.layers.19.mlp.up_proj
	- model.language_model.layers.19.mlp.down_proj
	- model.language_model.layers.20.self_attn.q_proj
	- model.language_model.layers.20.self_attn.k_proj
	- model.language_model.layers.20.self_attn.v_proj
	- model.language_model.layers.20.self_attn.o_proj
	- model.language_model.layers.20.mlp.gate_proj
	- model.language_model.layers.20.mlp.up_proj
	- model.language_model.layers.20.mlp.down_proj
	- model.language_model.layers.21.self_attn.q_proj
	- model.language_model.layers.21.self_attn.k_proj
	- model.language_model.layers.21.self_attn.v_proj
	- model.language_model.layers.21.self_attn.o_proj
	- model.language_model.layers.21.mlp.gate_proj
	- model.language_model.layers.21.mlp.up_proj
	- model.language_model.layers.21.mlp.down_proj
	- model.language_model.layers.22.self_attn.q_proj
	- model.language_model.layers.22.self_attn.k_proj
	- model.language_model.layers.22.self_attn.v_proj
	- model.language_model.layers.22.self_attn.o_proj
	- model.language_model.layers.22.mlp.gate_proj
	- model.language_model.layers.22.mlp.up_proj
	- model.language_model.layers.22.mlp.down_proj
	- model.language_model.layers.23.self_attn.q_proj
	- model.language_model.layers.23.self_attn.k_proj
	- model.language_model.layers.23.self_attn.v_proj
	- model.language_model.layers.23.self_attn.o_proj
	- model.language_model.layers.23.mlp.gate_proj
	- model.language_model.layers.23.mlp.up_proj
	- model.language_model.layers.23.mlp.down_proj
	- model.language_model.layers.24.self_attn.q_proj
	- model.language_model.layers.24.self_attn.k_proj
	- model.language_model.layers.24.self_attn.v_proj
	- model.language_model.layers.24.self_attn.o_proj
	- model.language_model.layers.24.mlp.gate_proj
	- model.language_model.layers.24.mlp.up_proj
	- model.language_model.layers.24.mlp.down_proj
	- model.language_model.layers.25.self_attn.q_proj
	- model.language_model.layers.25.self_attn.k_proj
	- model.language_model.layers.25.self_attn.v_proj
	- model.language_model.layers.25.self_attn.o_proj
	- model.language_model.layers.25.mlp.gate_proj
	- model.language_model.layers.25.mlp.up_proj
	- model.language_model.layers.25.mlp.down_proj
	- model.language_model.layers.26.self_attn.q_proj
	- model.language_model.layers.26.self_attn.k_proj
	- model.language_model.layers.26.self_attn.v_proj
	- model.language_model.layers.26.self_attn.o_proj
	- model.language_model.layers.26.mlp.gate_proj
	- model.language_model.layers.26.mlp.up_proj
	- model.language_model.layers.26.mlp.down_proj
	- model.language_model.layers.27.self_attn.q_proj
	- model.language_model.layers.27.self_attn.k_proj
	- model.language_model.layers.27.self_attn.v_proj
	- model.language_model.layers.27.self_attn.o_proj
	- model.language_model.layers.27.mlp.gate_proj
	- model.language_model.layers.27.mlp.up_proj
	- model.language_model.layers.27.mlp.down_proj
	- model.language_model.layers.28.self_attn.q_proj
	- model.language_model.layers.28.self_attn.k_proj
	- model.language_model.layers.28.self_attn.v_proj
	- model.language_model.layers.28.self_attn.o_proj
	- model.language_model.layers.28.mlp.gate_proj
	- model.language_model.layers.28.mlp.up_proj
	- model.language_model.layers.28.mlp.down_proj
	- model.language_model.layers.29.self_attn.q_proj
	- model.language_model.layers.29.self_attn.k_proj
	- model.language_model.layers.29.self_attn.v_proj
	- model.language_model.layers.29.self_attn.o_proj
	- model.language_model.layers.29.mlp.gate_proj
	- model.language_model.layers.29.mlp.up_proj
	- model.language_model.layers.29.mlp.down_proj
	- model.language_model.layers.30.self_attn.q_proj
	- model.language_model.layers.30.self_attn.k_proj
	- model.language_model.layers.30.self_attn.v_proj
	- model.language_model.layers.30.self_attn.o_proj
	- model.language_model.layers.30.mlp.gate_proj
	- model.language_model.layers.30.mlp.up_proj
	- model.language_model.layers.30.mlp.down_proj
	- model.language_model.layers.31.self_attn.q_proj
	- model.language_model.layers.31.self_attn.k_proj
	- model.language_model.layers.31.self_attn.v_proj
	- model.language_model.layers.31.self_attn.o_proj
	- model.language_model.layers.31.mlp.gate_proj
	- model.language_model.layers.31.mlp.up_proj
	- model.language_model.layers.31.mlp.down_proj
	- model.language_model.layers.32.self_attn.q_proj
	- model.language_model.layers.32.self_attn.k_proj
	- model.language_model.layers.32.self_attn.v_proj
	- model.language_model.layers.32.self_attn.o_proj
	- model.language_model.layers.32.mlp.gate_proj
	- model.language_model.layers.32.mlp.up_proj
	- model.language_model.layers.32.mlp.down_proj
	- model.language_model.layers.33.self_attn.q_proj
	- model.language_model.layers.33.self_attn.k_proj
	- model.language_model.layers.33.self_attn.v_proj
	- model.language_model.layers.33.self_attn.o_proj
	- model.language_model.layers.33.mlp.gate_proj
	- model.language_model.layers.33.mlp.up_proj
	- model.language_model.layers.33.mlp.down_proj
	- model.language_model.layers.34.self_attn.q_proj
	- model.language_model.layers.34.self_attn.k_proj
	- model.language_model.layers.34.self_attn.v_proj
	- model.language_model.layers.34.self_attn.o_proj
	- model.language_model.layers.34.mlp.gate_proj
	- model.language_model.layers.34.mlp.up_proj
	- model.language_model.layers.34.mlp.down_proj
	- model.language_model.layers.35.self_attn.q_proj
	- model.language_model.layers.35.self_attn.k_proj
	- model.language_model.layers.35.self_attn.v_proj
	- model.language_model.layers.35.self_attn.o_proj
	- model.language_model.layers.35.mlp.gate_proj
	- model.language_model.layers.35.mlp.up_proj
	- model.language_model.layers.35.mlp.down_proj
	- lm_head
	vision_gptq_int8_channel:
	method: GPTQ
	exception_to_default_vlm_policy: true
	weights:
	num_bits: 8
	type: int
	symmetric: true
	strategy: channel
	targets:
	- model.visual.blocks.0.attn.qkv
	- model.visual.blocks.0.attn.proj
	- model.visual.blocks.0.mlp.gate_proj
	- model.visual.blocks.0.mlp.up_proj
	- model.visual.blocks.0.mlp.down_proj
	- model.visual.blocks.1.attn.qkv
	- model.visual.blocks.1.attn.proj
	- model.visual.blocks.1.mlp.gate_proj
	- model.visual.blocks.1.mlp.up_proj
	- model.visual.blocks.1.mlp.down_proj
	- model.visual.blocks.2.attn.qkv
	- model.visual.blocks.2.attn.proj
	- model.visual.blocks.2.mlp.gate_proj
	- model.visual.blocks.2.mlp.up_proj
	- model.visual.blocks.2.mlp.down_proj
	- model.visual.blocks.3.attn.qkv
	- model.visual.blocks.3.attn.proj
	- model.visual.blocks.3.mlp.gate_proj
	- model.visual.blocks.3.mlp.up_proj
	- model.visual.blocks.3.mlp.down_proj
	- model.visual.blocks.4.attn.qkv
	- model.visual.blocks.4.attn.proj
	- model.visual.blocks.4.mlp.gate_proj
	- model.visual.blocks.4.mlp.up_proj
	- model.visual.blocks.4.mlp.down_proj
	- model.visual.blocks.5.attn.qkv
	- model.visual.blocks.5.attn.proj
	- model.visual.blocks.5.mlp.gate_proj
	- model.visual.blocks.5.mlp.up_proj
	- model.visual.blocks.5.mlp.down_proj
	- model.visual.blocks.6.attn.qkv
	- model.visual.blocks.6.attn.proj
	- model.visual.blocks.6.mlp.gate_proj
	- model.visual.blocks.6.mlp.up_proj
	- model.visual.blocks.6.mlp.down_proj
	- model.visual.blocks.7.attn.qkv
	- model.visual.blocks.7.attn.proj
	- model.visual.blocks.7.mlp.gate_proj
	- model.visual.blocks.7.mlp.up_proj
	- model.visual.blocks.7.mlp.down_proj
	- model.visual.blocks.8.attn.qkv
	- model.visual.blocks.8.attn.proj
	- model.visual.blocks.8.mlp.gate_proj
	- model.visual.blocks.8.mlp.up_proj
	- model.visual.blocks.8.mlp.down_proj
	- model.visual.blocks.9.attn.qkv
	- model.visual.blocks.9.attn.proj
	- model.visual.blocks.9.mlp.gate_proj
	- model.visual.blocks.9.mlp.up_proj
	- model.visual.blocks.9.mlp.down_proj
	- model.visual.blocks.10.attn.qkv
	- model.visual.blocks.10.attn.proj
	- model.visual.blocks.10.mlp.gate_proj
	- model.visual.blocks.10.mlp.up_proj
	- model.visual.blocks.10.mlp.down_proj
	- model.visual.blocks.11.attn.qkv
	- model.visual.blocks.11.attn.proj
	- model.visual.blocks.11.mlp.gate_proj
	- model.visual.blocks.11.mlp.up_proj
	- model.visual.blocks.11.mlp.down_proj
	- model.visual.blocks.12.attn.qkv
	- model.visual.blocks.12.attn.proj
	- model.visual.blocks.12.mlp.gate_proj
	- model.visual.blocks.12.mlp.up_proj
	- model.visual.blocks.12.mlp.down_proj
	- model.visual.blocks.13.attn.qkv
	- model.visual.blocks.13.attn.proj
	- model.visual.blocks.13.mlp.gate_proj
	- model.visual.blocks.13.mlp.up_proj
	- model.visual.blocks.13.mlp.down_proj
	- model.visual.blocks.14.attn.qkv
	- model.visual.blocks.14.attn.proj
	- model.visual.blocks.14.mlp.gate_proj
	- model.visual.blocks.14.mlp.up_proj
	- model.visual.blocks.14.mlp.down_proj
	- model.visual.blocks.15.attn.qkv
	- model.visual.blocks.15.attn.proj
	- model.visual.blocks.15.mlp.gate_proj
	- model.visual.blocks.15.mlp.up_proj
	- model.visual.blocks.15.mlp.down_proj
	- model.visual.blocks.16.attn.qkv
	- model.visual.blocks.16.attn.proj
	- model.visual.blocks.16.mlp.gate_proj
	- model.visual.blocks.16.mlp.up_proj
	- model.visual.blocks.16.mlp.down_proj
	- model.visual.blocks.17.attn.qkv
	- model.visual.blocks.17.attn.proj
	- model.visual.blocks.17.mlp.gate_proj
	- model.visual.blocks.17.mlp.up_proj
	- model.visual.blocks.17.mlp.down_proj
	- model.visual.blocks.18.attn.qkv
	- model.visual.blocks.18.attn.proj
	- model.visual.blocks.18.mlp.gate_proj
	- model.visual.blocks.18.mlp.up_proj
	- model.visual.blocks.18.mlp.down_proj
	- model.visual.blocks.19.attn.qkv
	- model.visual.blocks.19.attn.proj
	- model.visual.blocks.19.mlp.gate_proj
	- model.visual.blocks.19.mlp.up_proj
	- model.visual.blocks.19.mlp.down_proj
	- model.visual.blocks.20.attn.qkv
	- model.visual.blocks.20.attn.proj
	- model.visual.blocks.20.mlp.gate_proj
	- model.visual.blocks.20.mlp.up_proj
	- model.visual.blocks.20.mlp.down_proj
	- model.visual.blocks.21.attn.qkv
	- model.visual.blocks.21.attn.proj
	- model.visual.blocks.21.mlp.gate_proj
	- model.visual.blocks.21.mlp.up_proj
	- model.visual.blocks.21.mlp.down_proj
	- model.visual.blocks.22.attn.qkv
	- model.visual.blocks.22.attn.proj
	- model.visual.blocks.22.mlp.gate_proj
	- model.visual.blocks.22.mlp.up_proj
	- model.visual.blocks.22.mlp.down_proj
	- model.visual.blocks.23.attn.qkv
	- model.visual.blocks.23.attn.proj
	- model.visual.blocks.23.mlp.gate_proj
	- model.visual.blocks.23.mlp.up_proj
	- model.visual.blocks.23.mlp.down_proj
	- model.visual.blocks.24.attn.qkv
	- model.visual.blocks.24.attn.proj
	- model.visual.blocks.24.mlp.gate_proj
	- model.visual.blocks.24.mlp.up_proj
	- model.visual.blocks.24.mlp.down_proj
	- model.visual.blocks.25.attn.qkv
	- model.visual.blocks.25.attn.proj
	- model.visual.blocks.25.mlp.gate_proj
	- model.visual.blocks.25.mlp.up_proj
	- model.visual.blocks.25.mlp.down_proj
	- model.visual.blocks.26.attn.qkv
	- model.visual.blocks.26.attn.proj
	- model.visual.blocks.26.mlp.gate_proj
	- model.visual.blocks.26.mlp.up_proj
	- model.visual.blocks.26.mlp.down_proj
	- model.visual.blocks.27.attn.qkv
	- model.visual.blocks.27.attn.proj
	- model.visual.blocks.27.mlp.gate_proj
	- model.visual.blocks.27.mlp.up_proj
	- model.visual.blocks.27.mlp.down_proj
	- model.visual.blocks.28.attn.qkv
	- model.visual.blocks.28.attn.proj
	- model.visual.blocks.28.mlp.gate_proj
	- model.visual.blocks.28.mlp.up_proj
	- model.visual.blocks.28.mlp.down_proj
	- model.visual.blocks.29.attn.qkv
	- model.visual.blocks.29.attn.proj
	- model.visual.blocks.29.mlp.gate_proj
	- model.visual.blocks.29.mlp.up_proj
	- model.visual.blocks.29.mlp.down_proj
	- model.visual.blocks.30.attn.qkv
	- model.visual.blocks.30.attn.proj
	- model.visual.blocks.30.mlp.gate_proj
	- model.visual.blocks.30.mlp.up_proj
	- model.visual.blocks.30.mlp.down_proj
	- model.visual.blocks.31.attn.qkv
	- model.visual.blocks.31.attn.proj
	- model.visual.blocks.31.mlp.gate_proj
	- model.visual.blocks.31.mlp.up_proj
	- model.visual.blocks.31.mlp.down_proj
	- model.visual.merger.mlp.0
	- model.visual.merger.mlp.2