Instructions to use OpenGVLab/InternVL2-40B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-40B-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-40B-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 AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL2-40B-AWQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-40B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-40B-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": "OpenGVLab/InternVL2-40B-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/OpenGVLab/InternVL2-40B-AWQ

SGLang

How to use OpenGVLab/InternVL2-40B-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 "OpenGVLab/InternVL2-40B-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": "OpenGVLab/InternVL2-40B-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 "OpenGVLab/InternVL2-40B-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": "OpenGVLab/InternVL2-40B-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 OpenGVLab/InternVL2-40B-AWQ with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-40B-AWQ
```

czczup commited on Sep 24, 2024

Commit

dc39329

verified ·

1 Parent(s): 746114f

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

modeling_internvl_chat.py +6 -5

modeling_internvl_chat.py CHANGED Viewed

@@ -33,6 +33,7 @@ def version_cmp(v1, v2, op='eq'):
 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
     _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer']
@@ -97,7 +98,7 @@ class InternVLChatModel(PreTrainedModel):
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
         image_flags = image_flags.squeeze(-1)
-        input_embeds = self.language_model.get_input_embeddings()(input_ids)
         vit_embeds = self.extract_feature(pixel_values)
         vit_embeds = vit_embeds[image_flags == 1]
@@ -230,8 +231,8 @@ class InternVLChatModel(PreTrainedModel):
         tokenizer.padding_side = 'left'
         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(
@@ -279,8 +280,8 @@ class InternVLChatModel(PreTrainedModel):
             query = query.replace('<image>', image_tokens, 1)
         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,

 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
+    base_model_prefix = 'language_model'
     _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer']
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
         image_flags = image_flags.squeeze(-1)
+        input_embeds = self.language_model.get_input_embeddings()(input_ids).clone()
         vit_embeds = self.extract_feature(pixel_values)
         vit_embeds = vit_embeds[image_flags == 1]
         tokenizer.padding_side = 'left'
         model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
+        input_ids = model_inputs['input_ids'].to(self.device)
+        attention_mask = model_inputs['attention_mask'].to(self.device)
         eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             query = query.replace('<image>', image_tokens, 1)
         model_inputs = tokenizer(query, return_tensors='pt')
+        input_ids = model_inputs['input_ids'].to(self.device)
+        attention_mask = model_inputs['attention_mask'].to(self.device)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,