mistral-sft-v3 / README.md
andysalerno's picture
Update README.md
fe349da verified
|
raw
history blame
679 Bytes
metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
datasets:
  - andysalerno/ansalern-nectar-inputoutput

This is mistralai/Mistral-7B-v0.1, but with the special tokens added for ChatML, and then lightly finetuned with sft using a ChatML formatted dataset: andysalerno/ansalern-nectar-inputoutput

The training was very light, so while this model correctly follows ChatML formatting, it is not intended to be a chat model.

Rather, it is intended to be a base for further fine-tuning models that will use ChatML.