adamo1139's picture
Update README.md
fe62c74 verified
|
raw
history blame
402 Bytes
metadata
license: other
license_name: yi-license
license_link: LICENSE
tags:
  - finetune
  - fine-tune
datasets:
  - adamo1139/rawrr_v1

This model is Yi-34B-200K fine-tuned using DPO on rawrr_v1 dataset using QLoRA at ctx 200. I then merged the adapter with base model. This model is akin to raw LLaMa 65B, it's not meant to follow instructions but instead should be useful as base for further fine-tuning.