Instructions to use zwt123home123/InternVL2-4B-YOPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zwt123home123/InternVL2-4B-YOPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="zwt123home123/InternVL2-4B-YOPO", 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 AutoModel
model = AutoModel.from_pretrained("zwt123home123/InternVL2-4B-YOPO", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zwt123home123/InternVL2-4B-YOPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zwt123home123/InternVL2-4B-YOPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zwt123home123/InternVL2-4B-YOPO",
		"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/zwt123home123/InternVL2-4B-YOPO

SGLang

How to use zwt123home123/InternVL2-4B-YOPO 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 "zwt123home123/InternVL2-4B-YOPO" \
    --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": "zwt123home123/InternVL2-4B-YOPO",
		"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 "zwt123home123/InternVL2-4B-YOPO" \
        --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": "zwt123home123/InternVL2-4B-YOPO",
		"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 zwt123home123/InternVL2-4B-YOPO with Docker Model Runner:
```
docker model run hf.co/zwt123home123/InternVL2-4B-YOPO
```

zwt123home123 commited on Dec 9, 2024

Commit

a00443f

verified ·

1 Parent(s): 9f52557

Update modeling_phi3.py

Browse files

Files changed (1) hide show

modeling_phi3.py +3 -3

modeling_phi3.py CHANGED Viewed

@@ -328,9 +328,9 @@ class Phi3Attention(nn.Module):
         self.attncut = True
         self.headcut = True
         self.layercut = False
-        self.layercut_idx = 24
-        self.offset = 70
-        head_num=24
         self.mask = torch.load("headcut_mask/internvl2.0_4B/mask_"+str(head_num)+".pth")
     def _init_rope(self):

         self.attncut = True
         self.headcut = True
         self.layercut = False
+        self.layercut_idx = 24 # number of layer kept
+        self.offset = 70 # system prompt token length
+        head_num=24 # num of heads kept on average
         self.mask = torch.load("headcut_mask/internvl2.0_4B/mask_"+str(head_num)+".pth")
     def _init_rope(self):