Instructions to use jwu323/origin-llama-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jwu323/origin-llama-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jwu323/origin-llama-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jwu323/origin-llama-7b") model = AutoModelForCausalLM.from_pretrained("jwu323/origin-llama-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use jwu323/origin-llama-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jwu323/origin-llama-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jwu323/origin-llama-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jwu323/origin-llama-7b
- SGLang
How to use jwu323/origin-llama-7b 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 "jwu323/origin-llama-7b" \ --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": "jwu323/origin-llama-7b", "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 "jwu323/origin-llama-7b" \ --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": "jwu323/origin-llama-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jwu323/origin-llama-7b with Docker Model Runner:
docker model run hf.co/jwu323/origin-llama-7b
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This contains the original weights for the LLaMA-7b model. This model is under a non-commercial license (see the LICENSE file). You should only use this repository if you have been granted access to the model by filling out this form but either lost your copy of the weights or got some trouble converting them to the Transformers format.
According to this comment, dtype of a model in PyTorch is always float32, regardless of the dtype of the checkpoint you saved. If you load a float16 checkpoint in a model you create (which is in float32 by default), the dtype that is kept at the end is the dtype of the model, not the dtype of the checkpoint.
- Downloads last month
- 7