Instructions to use jnjj/LLaMa3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jnjj/LLaMa3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jnjj/LLaMa3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jnjj/LLaMa3") model = AutoModelForCausalLM.from_pretrained("jnjj/LLaMa3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jnjj/LLaMa3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jnjj/LLaMa3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jnjj/LLaMa3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jnjj/LLaMa3
- SGLang
How to use jnjj/LLaMa3 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 "jnjj/LLaMa3" \ --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": "jnjj/LLaMa3", "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 "jnjj/LLaMa3" \ --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": "jnjj/LLaMa3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jnjj/LLaMa3 with Docker Model Runner:
docker model run hf.co/jnjj/LLaMa3
Download training_args.bin from jnjj/LLaMa3: direct link, hf CLI and curl.
- Browser
- Download file 5.37 kB
-
https://huggingface.co/jnjj/LLaMa3/resolve/main/training_args.bin
- Command line
-
hf download hf://jnjj/LLaMa3/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/jnjj/LLaMa3/resolve/main/training_args.bin
5.37 kB
- Xet hash:
- f31123513051d31a2eb285a3350e99ba01e506ea8ed10e5380cf166eeeca3419
- Size of remote file:
- 5.37 kB
- SHA256:
- 33d05ed974c9168e4acca6749bc6434f914de01df97f176c7504d3d3233d2196
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.