Mistral-7B-Instruct-v0.2-refalign

mzhaoshuai/Mistral-7B-Instruct-v0.2-refalign

Mistral-7B-Instruct-v0.2-refalign is a text generation model from mzhaoshuai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

GitHub repository: https://github.com/mzhaoshuai/RefAlign

Downloads · 30 days

14% of all-time downloads

All-time downloads

111

Public

Parameters

7.2B

14.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.5 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: mistral
Access: Public
Created: Oct 9, 2025
Updated: Oct 16, 2025
SHA: d5354d92

Try a prompt

Base models

mistralai/Mistral-7B-Instruct-v0.2

Datasets

mzhaoshuai/Llama-3.3-70B-Inst-awq_ultrafeedback_1in3

Model card

From the Hugging Face model README

RefAlign: RL with Similarity-based Rewards

GitHub repository: https://github.com/mzhaoshuai/RefAlign

Paper: Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data.

The training data is mzhaoshuai/Llama-3.3-70B-Inst-awq_ultrafeedback_1in3.

When conducting Reinforcement Learning with Similarity-based Rewards, the reward function is BERTScore.

Hyper-Parameters	Value
LR	8e-7
Batch Size	512
Epoch	1
Prompt Length	400
Generation Length	800
Advantage CLIP	0.5
Sampled Generations (K)	2
BertScore Model	bart-large-mnli

Task: Text Generation
Library: transformers
Type: mistral
License: apache-2.0
Created: Oct 9, 2025
Updated: Oct 16, 2025