分流规则、重写写规则及脚本。

A high-throughput and memory-efficient inference and serving engine for LLMs

[try V7!] Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font for IDE and command line. 带连字和控制台图标的圆角等宽字体，中英文宽度完美2:1

SGLang is a fast serving framework for large language models and vision language models.

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention)

Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment

Data and code for paper "M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"

Obsidian plugin for OpenWeather API

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Large World Model -- Modeling Text and Video with Millions Context

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

[ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"

Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

A framework for few-shot evaluation of language models.

Must-read Papers on Large Language Model (LLM) Planning.

Implementation of RPPO(Risk-sensitive PPO) and RPBT(Population-based self-play with RPPO)

Summarize existing representative LLMs text datasets.

Go ahead and axolotl questions

OpenChat: Advancing Open-source Language Models with Imperfect Data

[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step

The implement of ACL2024: "MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization"

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

A learning environment for man-made Interactive Fiction games.

Reference implementation for DPO (Direct Preference Optimization)