llama2-coder-full / README.md
skar01's picture
Create README.md
97ded81
---
license: apache-2.0
---
Llama2 (7B) model fine-tuned on the CodeAlpaca 20k instructions dataset by using the method QLoRA with PEFT library.
Training and evaluation data 📚
CodeAlpaca_20K: contains 20K instruction-following data used for fine-tuning the Code Alpaca model.
Data is here: https://huggingface.co/mrm8488/falcon-7b-ft-codeAlpaca_20k
The adapter is here: https://huggingface.co/skar01/llama2-coder
The base model is: TinyPixel/Llama-2-7B-bf16-sharded