Phi-3-mini-4K-instruct with CPO-SimPO

3B

更新于6周前

6周前

34a183c778dd · 1.6GB

README

Phi-3-mini-4K-instruct with CPO-SimPO

使用 i-matrix calibration_datav3.txt 进行的量化
Saftensors 转换为 fp32

此仓库包含经 CPO-SimPO 技术增强的 Phi-3-mini-4K-instruct 模型。CPO-SimPO 结合了对比偏好优化（CPO）和简单偏好优化（SimPO）。

介绍

Phi-3-mini-4K-instruct 是一种针对指令任务进行优化的模型。这种方法已在关键基准测试中取得显著改进，推动了 AI 偏好学习的发展界限。

什么是 CPO-SimPO？

CPO-SimPO 是一种新技术，它结合了 CPO 和 SimPO 的元素。

对比偏好优化 (CPO): 添加行为克隆正则化器，确保模型保持在偏好数据分布附近。
简单偏好优化 (SimPO): 包含长度归一化和目标奖励边距，防止生成长而低质量的序列。

GitHub

模型性能

即将推出！

主要改进

增强模型性能: 显著的分数提升，特别是在 GSM8K（提高8.49分！）和 TruthfulQA（提高2.07分）。
质量控制: 通过长度归一化和奖励边距改进高质量序列的生成。
平衡优化: BC正则化器帮助保持学习到的偏好完整性，同时不偏离偏好数据分布。

# Phi-3-mini-4K-instruct with CPO-SimPO

- Quantizations with i-matrix `calibration_datav3.txt`
- Saftensors converted to fp32

This repository contains the Phi-3-mini-4K-instruct model enhanced with the CPO-SimPO technique. CPO-SimPO combines Contrastive Preference Optimization (CPO) and Simple Preference Optimization (SimPO).

## Introduction

Phi-3-mini-4K-instruct is a model optimized for instruction-based tasks. This approach has demonstrated notable improvements in key benchmarks, pushing the boundaries of AI preference learning.

### What is CPO-SimPO?

CPO-SimPO is a novel technique, which combines elements from CPO and SimPO:

- **Contrastive Preference Optimization (CPO):** Adds a behavior cloning regularizer to ensure the model remains close to the preferred data distribution.
- **Simple Preference Optimization (SimPO):** Incorporates length normalization and target reward margins to prevent the generation of long but low-quality sequences.

### Github

**[CPO-SIMPO](https://github.com/fe1ixxu/CPO_SIMPO)**

## Model Performance

COMING SOON!

### Key Improvements:
- **Enhanced Model Performance:** Significant score improvements, particularly in GSM8K (up by 8.49 points!) and TruthfulQA (up by 2.07 points).
- **Quality Control:** Improved generation of high-quality sequences through length normalization and reward margins.
- **Balanced Optimization:** The BC regularizer helps maintain the integrity of learned preferences without deviating from the preferred data distribution.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)