Instruction Makes a Difference
Paper • 2402.00453 • Published
How to use from
SGLangUse 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 "tosin/LLaDoc" \
--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": "tosin/LLaDoc",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
LLaDoc (Large Language and Document) model
This is a fine-tuned model of LLaVA1.5 (7B) on the iDocVQA dataset. It is intended to be used as a multimodal system. The dataset it's trained on is limited in scope, as it covers only certain domains.
The accuracy achieved on the validation set is 29.58%.
Please find the information about preprocessing, training and full details of the LLaVA model in the original link
The paper for this work is available on arXiv: https://arxiv.org/abs/2402.00453
- Downloads last month
- 4
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "tosin/LLaDoc" \ --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": "tosin/LLaDoc", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'