Instructions to use OpenGVLab/InternVL-Chat-V1-2-Plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL-Chat-V1-2-Plus with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL-Chat-V1-2-Plus", 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("OpenGVLab/InternVL-Chat-V1-2-Plus", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL-Chat-V1-2-Plus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL-Chat-V1-2-Plus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL-Chat-V1-2-Plus",
		"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/OpenGVLab/InternVL-Chat-V1-2-Plus

SGLang

How to use OpenGVLab/InternVL-Chat-V1-2-Plus 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 "OpenGVLab/InternVL-Chat-V1-2-Plus" \
    --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": "OpenGVLab/InternVL-Chat-V1-2-Plus",
		"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 "OpenGVLab/InternVL-Chat-V1-2-Plus" \
        --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": "OpenGVLab/InternVL-Chat-V1-2-Plus",
		"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 OpenGVLab/InternVL-Chat-V1-2-Plus with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL-Chat-V1-2-Plus
```

czczup commited on Mar 25, 2024

Commit

3b63e0f

verified ·

1 Parent(s): c5f6e4f

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

modeling_internvl_chat.py +15 -6
runs/Feb18_13-14-12_SH-IDC1-10-140-37-8/events.out.tfevents.1708234550.SH-IDC1-10-140-37-8.124298.0 +3 -0
runs/Feb18_14-05-57_SH-IDC1-10-140-37-8/events.out.tfevents.1708237619.SH-IDC1-10-140-37-8.185381.0 +3 -0

modeling_internvl_chat.py CHANGED Viewed

@@ -375,7 +375,7 @@ class InternVLChatModel(PreTrainedModel):
         vit_embeds = self.mlp1(vit_embeds)
         return vit_embeds
-    def chat(self, tokenizer, pixel_values, question, generation_config,
              IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>'):
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
@@ -384,8 +384,15 @@ class InternVLChatModel(PreTrainedModel):
         from .conversation import get_conv_template
         template = get_conv_template(self.template)
-        image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token + IMG_END_TOKEN
-        template.append_message(template.roles[0], image_tokens + '\n' + question)
         template.append_message(template.roles[1], None)
         query = template.get_prompt()
         model_inputs = tokenizer(query, return_tensors='pt')
@@ -399,9 +406,11 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
-        query_to_print = query.replace(image_tokens, '<image>')
-        print(query_to_print, response)
-        return response
     @torch.no_grad()
     def generate(

         vit_embeds = self.mlp1(vit_embeds)
         return vit_embeds
+    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
              IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>'):
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
         from .conversation import get_conv_template
         template = get_conv_template(self.template)
+        if history is None:
+            history = []
+            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token + IMG_END_TOKEN
+            question = image_tokens + '\n' + question
+        else:
+            for (old_question, old_answer) in history:
+                template.append_message(template.roles[0], old_question)
+                template.append_message(template.roles[1], old_answer)
+        template.append_message(template.roles[0], question)
         template.append_message(template.roles[1], None)
         query = template.get_prompt()
         model_inputs = tokenizer(query, return_tensors='pt')
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
+        history.append((question, response))
+        if return_history:
+            return response, history
+        else:
+            return response
     @torch.no_grad()
     def generate(

runs/Feb18_13-14-12_SH-IDC1-10-140-37-8/events.out.tfevents.1708234550.SH-IDC1-10-140-37-8.124298.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0813499a41ad34fcc8faf77fee66dc139237be21fbd16e9abfaab6d39aebb8a
+size 8764

runs/Feb18_14-05-57_SH-IDC1-10-140-37-8/events.out.tfevents.1708237619.SH-IDC1-10-140-37-8.185381.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf844c1015f2b40fa8e152da5dce2540ea0f210cbcc59c30e0bf70be62d85f7
+size 507325