metadata

base_model: nbeerbower/bophades-mistral-math-DPO-7B
datasets:
  - kyujinpy/orca_math_dpo
inference: false
library_name: transformers
license: apache-2.0
merged_models:
  - nbeerbower/bophades-v2-mistral-7B
pipeline_tag: text-generation
quantized_by: Suparious
tags:
  - 4-bit
  - AWQ
  - text-generation
  - autotrain_compatible
  - endpoints_compatible

nbeerbower/bophades-mistral-math-DPO-7B AWQ

Model creator: nbeerbower
Original model: bophades-mistral-math-DPO-7B

Model Summary

bophades-v2-mistral-7B finetuned on kyujinpy/orca_math_dpo.

Finetuned using an A100 on Google Colab. 🙏

Fine-tune a Mistral-7b model with Direct Preference Optimization - Maxime Labonne