b4rtaz's picture
Update README.md
81e048e verified
|
raw
history blame
656 Bytes
metadata
license: llama3

This is converted Llama 3 8B model to Distributed Llama format. The model is quantized to Q40.

πŸš€ How to Run?

  1. ⏬ Download this repository.
  2. ⏬ Download Distributed Llama repository.
  3. πŸ”¨ Build Distributed Llama:
make dllama
  1. πŸš€ Run Distributed Llama:
./dllama inference --prompt "Hello world" --model dllama_model_meta-llama-3-8b_q40.m --tokenizer dllama_tokenizer_llama3.t --buffer-float-type q80 --nthreads 4

🎩 License

Llama 3 Community License