Instructions to use kchoi/llama-7b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kchoi/llama-7b-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kchoi/llama-7b-hf")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kchoi/llama-7b-hf") model = AutoModelForCausalLM.from_pretrained("kchoi/llama-7b-hf") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use kchoi/llama-7b-hf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kchoi/llama-7b-hf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kchoi/llama-7b-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kchoi/llama-7b-hf
- SGLang
How to use kchoi/llama-7b-hf 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 "kchoi/llama-7b-hf" \ --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": "kchoi/llama-7b-hf", "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 "kchoi/llama-7b-hf" \ --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": "kchoi/llama-7b-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kchoi/llama-7b-hf with Docker Model Runner:
docker model run hf.co/kchoi/llama-7b-hf
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
LLama 7B Hugging Face model
This repo hosts model weights and it's for research purpose. If it against some policies that I don't know, feel free to reach out to me and I will delete it.
license: other
LLaMA-7B converted to work with Transformers/HuggingFace. This is under a special license, please see the LICENSE file for details.
License Non-commercial bespoke license
Note: I copied above statement from https://huggingface.co/decapoda-research/llama-7b-hf
- Downloads last month
- 7