Instructions to use OpenGVLab/InternVL-Chat-V1-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL-Chat-V1-5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL-Chat-V1-5", 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-V1-5", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL-Chat-V1-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL-Chat-V1-5"
# 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-V1-5",
		"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-V1-5

SGLang

How to use OpenGVLab/InternVL-Chat-V1-5 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-V1-5" \
    --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-V1-5",
		"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-V1-5" \
        --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-V1-5",
		"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-V1-5 with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL-Chat-V1-5
```

czczup commited on May 28, 2024

Commit

1352871

verified ·

1 Parent(s): 40b10d5

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

modeling_internvl_chat.py +6 -11

modeling_internvl_chat.py CHANGED Viewed

@@ -26,7 +26,7 @@ logger = logging.get_logger(__name__)
 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
-    _no_split_modules = ['InternVisionEncoderLayer', 'LlamaDecoderLayer']
     def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):
         super().__init__(config)
@@ -237,10 +237,6 @@ class InternVLChatModel(PreTrainedModel):
             raise NotImplementedError
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
         self.img_context_token_id = img_context_token_id
-        if tokenizer.convert_tokens_to_ids('<|im_end|>') != 0:
-            eos_token_id = tokenizer.convert_tokens_to_ids('<|im_end|>')  # 92542, InternLM2
-        else:
-            eos_token_id = tokenizer.eos_token_id
         from .conversation import get_conv_template
@@ -259,6 +255,7 @@ class InternVLChatModel(PreTrainedModel):
         model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
         input_ids = model_inputs['input_ids'].cuda()
         attention_mask = model_inputs['attention_mask'].cuda()
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
@@ -268,7 +265,7 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
-        responses = [response.split('<|im_end|>')[0].strip() for response in responses]  # for InternLM2
         return responses
     def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
@@ -276,10 +273,6 @@ class InternVLChatModel(PreTrainedModel):
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
         self.img_context_token_id = img_context_token_id
-        if tokenizer.convert_tokens_to_ids('<|im_end|>') != 0:
-            eos_token_id = tokenizer.convert_tokens_to_ids('<|im_end|>')  # 92542, InternLM2
-        else:
-            eos_token_id = tokenizer.eos_token_id
         from .conversation import get_conv_template
@@ -300,7 +293,9 @@ class InternVLChatModel(PreTrainedModel):
         model_inputs = tokenizer(query, return_tensors='pt')
         input_ids = model_inputs['input_ids'].cuda()
         attention_mask = model_inputs['attention_mask'].cuda()
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,
             input_ids=input_ids,
@@ -308,7 +303,7 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
-        response = response.split('<|im_end|>')[0].strip()  # for InternLM2
         history.append((question, response))
         if return_history:
             return response, history

 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
+    _no_split_modules = ['InternVisionEncoderLayer', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
     def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):
         super().__init__(config)
             raise NotImplementedError
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
         self.img_context_token_id = img_context_token_id
         from .conversation import get_conv_template
         model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
         input_ids = model_inputs['input_ids'].cuda()
         attention_mask = model_inputs['attention_mask'].cuda()
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             **generation_config
         )
         responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
+        responses = [response.split(template.sep)[0].strip() for response in responses]
         return responses
     def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
         img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
         self.img_context_token_id = img_context_token_id
         from .conversation import get_conv_template
         model_inputs = tokenizer(query, return_tensors='pt')
         input_ids = model_inputs['input_ids'].cuda()
         attention_mask = model_inputs['attention_mask'].cuda()
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,
             input_ids=input_ids,
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
+        response = response.split(template.sep)[0].strip()
         history.append((question, response))
         if return_history:
             return response, history