Pinned Loading

1. LlamaFactory LlamaFactory Public

   Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

   Python 67k 8.1k

2. EasyR1 EasyR1 Public

   EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

   Python 4.6k 354

3. ChatGLM-Efficient-Tuning ChatGLM-Efficient-Tuning Public archive

   Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

   Python 3.7k 472

4. FastEdit FastEdit Public

   🩹Editing large language models within 10 seconds⚡

   Python 1.4k 102

5. AMP-Regularizer AMP-Regularizer Public

   Code for our paper "Regularizing Neural Networks via Adversarial Model Perturbation", CVPR2021

   Python 40 11

6. MathRuler MathRuler Public

   A light-weight tool for evaluating LLMs in rule-based ways.

   Python 84 9