README.md

metadata

library_name: transformers
base_model:
  - nbeerbower/Hermes2-Gutenberg2-Mistral-7B
datasets:
  - flammenai/Date-DPO-NoAsterisks
  - jondurbin/truthy-dpo-v0.1
license: apache-2.0

QuantFactory/Flammades-Mistral-7B-GGUF

This is quantized version of flammenai/Flammades-Mistral-7B created using llama.cpp

Original Model Card

Flammades-Mistral-7B

nbeerbower/Hermes2-Gutenberg2-Mistral-7B finetuned on flammenai/Date-DPO-NoAsterisks and jondurbin/truthy-dpo-v0.1.

Method

ORPO tuned with 2x RTX 3090 for 3 epochs.