Instructions to use ConvLLaVA/ConvLLaVA-sft-768 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ConvLLaVA/ConvLLaVA-sft-768 with Transformers:

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

pipe = pipeline("text-generation", model="ConvLLaVA/ConvLLaVA-sft-768")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("ConvLLaVA/ConvLLaVA-sft-768")
model = AutoModelForCausalLM.from_pretrained("ConvLLaVA/ConvLLaVA-sft-768")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ConvLLaVA/ConvLLaVA-sft-768 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ConvLLaVA/ConvLLaVA-sft-768"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ConvLLaVA/ConvLLaVA-sft-768",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ConvLLaVA/ConvLLaVA-sft-768

SGLang

How to use ConvLLaVA/ConvLLaVA-sft-768 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 "ConvLLaVA/ConvLLaVA-sft-768" \
    --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": "ConvLLaVA/ConvLLaVA-sft-768",
		"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 "ConvLLaVA/ConvLLaVA-sft-768" \
        --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": "ConvLLaVA/ConvLLaVA-sft-768",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ConvLLaVA/ConvLLaVA-sft-768 with Docker Model Runner:
```
docker model run hf.co/ConvLLaVA/ConvLLaVA-sft-768
```

ConvLLaVA Model Card

Model details

Model type: ConvLLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: lmsys/vicuna-7b-v1.5

Model date: ConvLLaVA-768 was trained in March 2024.

Paper or resources for more information: https://github.com/alibaba/conv-llava/

License

Where to send questions or comments about the model: https://github.com/alibaba/conv-llava/issues

Intended use

Primary intended uses: The primary use of ConvLLaVA is research on large multimodal models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

1.2M ShareGPT4V-PT caption data.
100K ShareGPT4V caption data.
1.4M ALLaVA caption and instruction data.
186K VFLAN multitask data.
158K GPT-generated multimodal instruction-following data.
500K academic-task-oriented VQA data mixture.
40K ShareGPT data.

Paper

arxiv.org/abs/2405.15738

Downloads last month: 12

Dataset used to train ConvLLaVA/ConvLLaVA-sft-768

Collection including ConvLLaVA/ConvLLaVA-sft-768

ConvLLaVA

Collection

A collection of ConvLLaVA models. • 10 items • Updated May 28, 2024 • 10

Paper for ConvLLaVA/ConvLLaVA-sft-768

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

Paper • 2405.15738 • Published May 24, 2024 • 46