README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
  - trl
base_model: unsloth/mistral-7b-v0.2-bnb-4bit

A fishy model

Trained with the ChatML format with a max context length of 32k.

Average length in datasets is around 4-8k tokens.

Uploaded model

• Developed by: TheTsar1209
• License: apache-2.0
• Finetuned from model : unsloth/mistral-7b-v0.2-bnb-4bit

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.