This is converted TinyLlama-1.1B-3T model to Distributed Llama format. The model is quantized to Q40.
π How to Run?
- β¬ Download this repository.
- β¬ Download Distributed Llama repository.
- π¨ Build Distributed Llama:
make dllama
- π Run Distributed Llama:
./dllama chat --model dllama_model_tinylama_1.1b_3t_q40.m --tokenizer dllama_tokenizer_tinylama_1.1b_3t.t --buffer-float-type q80 --nthreads 4
π© License
Apache 2.0