ComparisonPO
/

Mistral-Base-7B-DPO_clean

Model card Files Files and versions

DPO model excluding the noisy preference pairs for Mistral-Base under trl/ultradeedback_binarized finetuning.

Downloads last month: 8

Safetensors

Model size

7B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ComparisonPO/Mistral-Base-7B-DPO_clean

Base model

mistralai/Mistral-7B-v0.1

Finetuned

alignment-handbook/zephyr-7b-sft-full

Finetuned

(390)

this model

Finetunes

Dataset used to train ComparisonPO/Mistral-Base-7B-DPO_clean