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

Libraries

How to use OpenGVLab/InternVL2-Pretrain-Models with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-Pretrain-Models", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL2-Pretrain-Models", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-Pretrain-Models with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-Pretrain-Models"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL2-Pretrain-Models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenGVLab/InternVL2-Pretrain-Models

SGLang

How to use OpenGVLab/InternVL2-Pretrain-Models 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-Pretrain-Models" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL2-Pretrain-Models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-Pretrain-Models" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL2-Pretrain-Models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenGVLab/InternVL2-Pretrain-Models with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-Pretrain-Models
```

czczup commited on Dec 7, 2024

Commit

3d946dc

verified ·

1 Parent(s): a8052c0

Release InternVL 2.0 pretrained models

Browse files

Files changed (2) hide show

InternVL2-40B-Pretrain/configuration_internvl_chat.py +2 -2
InternVL2-40B-Pretrain/modeling_intern_vit.py +1 -0

InternVL2-40B-Pretrain/configuration_internvl_chat.py CHANGED Viewed

@@ -38,11 +38,11 @@ class InternVLChatConfig(PretrainedConfig):
         super().__init__(**kwargs)
         if vision_config is None:
-            vision_config = {}
             logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
         if llm_config is None:
-            llm_config = {}
             logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
         self.vision_config = InternVisionConfig(**vision_config)

         super().__init__(**kwargs)
         if vision_config is None:
+            vision_config = {'architectures': ['InternVisionModel']}
             logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
         if llm_config is None:
+            llm_config = {'architectures': ['LlamaForCausalLM']}
             logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
         self.vision_config = InternVisionConfig(**vision_config)

InternVL2-40B-Pretrain/modeling_intern_vit.py CHANGED Viewed

@@ -3,6 +3,7 @@
 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 from typing import Optional, Tuple, Union
 import torch

 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 from typing import Optional, Tuple, Union
 import torch