Instructions to use harpertoken/chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use harpertoken/chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="harpertoken/chat")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("harpertoken/chat") model = AutoModelForCausalLM.from_pretrained("harpertoken/chat", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use harpertoken/chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "harpertoken/chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "harpertoken/chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/harpertoken/chat
- SGLang
How to use harpertoken/chat 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 "harpertoken/chat" \ --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": "harpertoken/chat", "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 "harpertoken/chat" \ --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": "harpertoken/chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use harpertoken/chat with Docker Model Runner:
docker model run hf.co/harpertoken/chat
Commit History
Upload README.md with huggingface_hub 1d8b417 verified
Upload README.md with huggingface_hub ccaebb6 verified
Upload README.md with huggingface_hub 27de642 verified
Upload README.md with huggingface_hub 18eb0ba verified
Upload README.md with huggingface_hub 07fca43 verified
Update README.md 0465329 verified
Update README.md f824027 verified
Add Related Models and Model Differences sections for truthful discussion 7999200
bniladridas commited on
Correct README: update base model to gpt2 and max sequence length to 1024 19d9673
bniladridas commited on
Update README with cleaned up content and correct references 38a5da1
bniladridas commited on
Update README.md 9919666 verified
Niladri Das π¦ commited on
Update README.md 7cfa67b verified
Niladri Das π¦ commited on
Update README.md db3b279 verified
Niladri Das π¦ commited on
Update README.md 91f54d2 verified
Niladri Das π¦ commited on
initial commit dd2d947 verified
Niladri Das π¦ commited on