NEW Code for SFT and DPO Training: Unsloth LLama

2 free Jupyter Notebooks from UNSLOTH: Supervised Fine-Tuning and DPO-Alignment of your LLM (LLama or Mistral), compatible with HuggingFace SFT and DPO-Trainer script.

All rights with UNSLOTH:

https://github.com/unslothai/unsloth

Alpaca_+_Mistral_7b_full_Unsloth_example.ipynb:
https://colab.research.google.com/#fileId=https://huggingface.co/datasets/unsloth/notebooks/blob/main/Alpaca_%2B_Mistral_7b_full_example.ipynb

DPO_Zephyr_Unsloth_Example.ipynb
https://colab.research.google.com/#fileId=https://huggingface.co/datasets/unsloth/notebooks/blob/main/DPO_Zephyr_Unsloth_Example.ipynb

#ai
#pythoncoding
#airesearch

alignment code fine-tuning free huggingface jupyter jupyter notebooks llama llama 2 llm mistral notebooks rights sft supervised fine-tuning trainer training