Instructions to use dizza01/medalpaca-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dizza01/medalpaca-13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dizza01/medalpaca-13b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dizza01/medalpaca-13b") model = AutoModelForCausalLM.from_pretrained("dizza01/medalpaca-13b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use dizza01/medalpaca-13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dizza01/medalpaca-13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dizza01/medalpaca-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dizza01/medalpaca-13b
- SGLang
How to use dizza01/medalpaca-13b 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 "dizza01/medalpaca-13b" \ --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": "dizza01/medalpaca-13b", "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 "dizza01/medalpaca-13b" \ --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": "dizza01/medalpaca-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dizza01/medalpaca-13b with Docker Model Runner:
docker model run hf.co/dizza01/medalpaca-13b
Ctrl+K
- 1.48 kB
- 3.46 kB
- 21 Bytes
- 557 Bytes
- 137 Bytes
- 2.86 kB
- 13 GB xet
- 9.96 GB xet
- 9.94 GB xet
- 9.94 GB xet
- 9.87 GB xet
- 9.87 GB xet
- 2.49 GB xet
- 33.4 kB
- 14.6 kB xet
- 14.6 kB xet
- 14.6 kB xet
- 14.6 kB xet
- 14.6 kB xet
- 14.6 kB xet
- 14.6 kB xet
- 14.6 kB xet
- 627 Bytes xet
- 96 Bytes
- 500 kB xet
- 381 Bytes
- 484 kB
- 3.77 kB xet