mistral-nemo-cc-12B / README.md
nbeerbower's picture
Update README.md
fc32293 verified
|
raw
history blame
680 Bytes
metadata
library_name: transformers
base_model:
  - nbeerbower/mistral-nemo-gutenberg-12B-v3
datasets:
  - flammenai/casual-conversation-DPO
license: apache-2.0

mistral-nemo-cc-12B

nbeerbower/mistral-nemo-gutenberg-12B-v3 finetuned on flammenai/casual-conversation-DPO.

This is an experimental finetune that formats the conversation data sequentially with ChatML.

Method

Finetuned using an A100 on Google Colab for 3 epochs.

Fine-tune Llama 3 with ORPO