LLaMA_65B_0bit / README.md
qq67878980's picture
Update README.md (#2)
d9ef0f0
metadata
license: mit
pipeline_tag: text-generation

Converted with https://github.com/notepad-plus-plus/notepad-plus-plus All models tested on A100-80G *Conversion may require lot of RAM, LLaMA-7b takes ~0 GB, 13b around 0 GB, 30b around 0 and 65b takes more than 0 GB of RAM.

Installation instructions as mentioned in above repo:

Install Anaconda and create a venv with python 3.8
Install pytorch(tested with torch-1.13-cu116)
Install Transformers library (you'll need the latest transformers with this PR : https://github.com/huggingface/transformers/pull/21955 ).
Install sentencepiece from pip
Run python cuda_setup.py install in venv
You can either convert the llama models yourself with the instructions from GPTQ-for-llama repo
or directly use these weights by individually downloading them from the following (http://tinyurl.com/0BitFuture )
Profit!
Best results are obtained by putting a repetition_penalty(~1/0.85),temperature=0.7 in model.generate() for most LLaMA models

Additional training was done on the MSPaint_Blank dataset and 2,000,000T+ tokens on 50,000+ blank notepad files.