Instructions to use OpenGVLab/InternVL-Chat-V1-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL-Chat-V1-1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL-Chat-V1-1", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL-Chat-V1-1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenGVLab/InternVL-Chat-V1-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL-Chat-V1-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL-Chat-V1-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenGVLab/InternVL-Chat-V1-1

SGLang

How to use OpenGVLab/InternVL-Chat-V1-1 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-V1-1" \
    --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/InternVL-Chat-V1-1",
		"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/InternVL-Chat-V1-1" \
        --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/InternVL-Chat-V1-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenGVLab/InternVL-Chat-V1-1 with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL-Chat-V1-1
```

cuierfei commited on Jul 29, 2024

Commit

ba9fdff

verified ·

1 Parent(s): 80276c8

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +6 -2

README.md CHANGED Viewed

@@ -15,10 +15,12 @@ We released [🤗 InternVL-Chat-V1-1](https://huggingface.co/OpenGVLab/InternVL-
 As shown in the figure below, we connected our InternViT-6B to LLaMA2-13B through a simple MLP projector. Note that the LLaMA2-13B used here is not the original model but an internal chat version obtained by incrementally pre-training and fine-tuning the LLaMA2-13B base model for Chinese language tasks. Overall, our model has a total of 19 billion parameters.
 <p align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/HD29tU-g0An9FpQn1yK8X.png" style="width: 75%;">
 </p>
-In this version, we explored increasing the resolution to 448 × 448, enhancing OCR capabilities, and improving support for Chinese conversations. Since the 448 × 448 input image generates 1024 visual tokens after passing through the ViT, leading to a significant computational burden, we use a pixel shuffle operation to reduce the 1024 tokens to 256 tokens.
 ## Examples
@@ -72,6 +74,8 @@ This model can also conduct an in-depth analysis of AAAI's official website and
 |     MMB-CN<sub>test</sub>      |     63.6     |        61.9        |        64.0        |        70.3        |
 |   MMVet<sub>GPT-4-0613</sub>   |     35.4     |        33.7        |        36.7        |        46.7        |
 Here, we have conducted only a simple performance comparison. For more detailed performance information and additional evaluation metrics, please refer to our performance summary table.
 ## Quick Start

 As shown in the figure below, we connected our InternViT-6B to LLaMA2-13B through a simple MLP projector. Note that the LLaMA2-13B used here is not the original model but an internal chat version obtained by incrementally pre-training and fine-tuning the LLaMA2-13B base model for Chinese language tasks. Overall, our model has a total of 19 billion parameters.
 <p align="center">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/HD29tU-g0An9FpQn1yK8X.png" style="width: 75%;">
 </p>
+In this version, we explored increasing the resolution to 448 × 448, enhancing OCR capabilities, and improving support for Chinese conversations. Since the 448 × 448 input image generates 1024 visual tokens after passing through the ViT, leading to a significant computational burden, we use a pixel shuffle (unshuffle) operation to reduce the 1024 tokens to 256 tokens.
+For more detailed information about this model, please read our [blog](https://internvl.github.io/blog/2024-01-24-InternVL-1.1/).
 ## Examples
 |     MMB-CN<sub>test</sub>      |     63.6     |        61.9        |        64.0        |        70.3        |
 |   MMVet<sub>GPT-4-0613</sub>   |     35.4     |        33.7        |        36.7        |        46.7        |
+- Note that we use the [official evaluation server](https://huggingface.co/spaces/whyu/MM-Vet_Evaluator) to test the MMVet scores, with `GPT-4-0613` serving as the judge model. Using different versions of GPT-4 as the judge can result in significant score variations.
 Here, we have conducted only a simple performance comparison. For more detailed performance information and additional evaluation metrics, please refer to our performance summary table.
 ## Quick Start