b4rtaz's picture
Update README.md
3225410 verified
|
raw
history blame
771 Bytes
metadata
license: llama3.2
tags:
  - distributed-inference
  - text-generation

This is converted Llama 3.2 1B Instruct 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 chat --model dllama_model_llama3_2_1b_instruct_q40.m --tokenizer dllama_tokenizer_llama3_2_1b_instruct_q40.t --buffer-float-type q80 --nthreads 4 --max-seq-len 8192

🎩 License

Llama 3.2 Community License