metadata
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: LeroyDyer/Mixtral_AI_MiniTron_SFT
datasets:
- abacusai/ARC_DPO_FewShot
- abacusai/MetaMathFewshot
- abacusai/HellaSwag_DPO_FewShot
- yahma/alpaca-cleaned
- iamtarun/python_code_instructions_18k_alpaca
- gate369/Alpaca-Star
This model is under training ! requires data !! : and time ! (day by day will add 1hr of dolphin Coder/White rabbit (generally and orca/dolphin ) until the datasets are fully overfit! before applying other datasets)
Getting better ! under training ( the base model become the updated version , this model is always in training and changing if a problem happens he can revert to his previous base self: )
Uploaded model
- Developed by: LeroyDyer
- License: apache-2.0
- Finetuned from model : Mixtral_AI_MiniTron
Recently upated with a few more datasets::::: (Still not ready to talkabout !) (converging quickly on datasets)
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.