Note Annotated paper and personal notes coming soon!

HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1

Text Generation • Updated Apr 18 • 220 • 262

Note ORPO full fine-tune of `mistral-community/Mixtral-8x22B-v0.1` with `argilla/distilabel-capybara-dpo-7k-binarized` with ChatML formatting (in collaboration with Hugging Face, Argilla and Kaist AI)

alvarobartt/mistral-orpo-mix

Text Generation • Updated Mar 24 • 29 • 1

Note ORPO full fine-tune of `mistralai/Mistral-7B-v0.1` with `alvarobartt/dpo-mix-7k-simplified` with ChatML formatting

alvarobartt/Mistral-7B-v0.1-ORPO

Text Generation • Updated Mar 23 • 44 • 14

Note ORPO fine-tune of `mistralai/Mistral-7B-v0.1` with `alvarobartt/dpo-mix-7k-simplified` with ChatML formatting using QLoRA (weights are merged into base model)

alvarobartt/Mistral-7B-v0.1-ORPO-PEFT

Text Generation • Updated Mar 23 • 4 • 1

Note ORPO fine-tune of `mistralai/Mistral-7B-v0.1` with `alvarobartt/dpo-mix-7k-simplified` with ChatML formatting using QLoRA (only contains the adapter, for merged weights check `alvarobartt/Mistral-7B-v0.1-ORPO`)