b4rtaz's picture
Update README.md
91900c0 verified
|
raw
history blame
715 Bytes
---
license: apache-2.0
tags:
- distributed-inference
- text-generation
---
This is converted [TinyLlama-1.1B-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) model to [Distributed Llama](https://github.com/b4rtaz/distributed-llama) format. The model is quantized to Q40.
## πŸš€ How to Run?
1. ⏬ Download this repository.
2. ⏬ Download [Distributed Llama](https://github.com/b4rtaz/distributed-llama) repository.
3. πŸ”¨ Build Distributed Llama:
```
make dllama
```
4. πŸš€ 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
```
## 🎩 License
Apache 2.0