Instructions to use ArushBuilds/Pragya-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArushBuilds/Pragya-Preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ArushBuilds/Pragya-Preview")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ArushBuilds/Pragya-Preview", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ArushBuilds/Pragya-Preview with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ArushBuilds/Pragya-Preview" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ArushBuilds/Pragya-Preview", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ArushBuilds/Pragya-Preview
- SGLang
How to use ArushBuilds/Pragya-Preview 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 "ArushBuilds/Pragya-Preview" \ --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": "ArushBuilds/Pragya-Preview", "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 "ArushBuilds/Pragya-Preview" \ --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": "ArushBuilds/Pragya-Preview", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ArushBuilds/Pragya-Preview with Docker Model Runner:
docker model run hf.co/ArushBuilds/Pragya-Preview
Commit History
Upload model.onnx 93a5471 verified
Update README.md 2a2243e verified
Update README.md 63313eb verified
Update README.md 00106e1 verified
Update README.md aed0fb8 verified
Update README.md db00923 verified
Update README.md 63cb224 verified
Update README.md aa2b4b7 verified
Update README.md f2f509a verified
Update README.md f33dc65 verified
Create README.md 9e536d1 verified
Upload pragya.pt 430566a verified
initial commit ed91ef7 verified
Arush kumar commited on