Tesseract Open Source OCR Engine (main repository)

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Proximal Policy Optimization(PPO) with Intrinsic Curiosity Module(ICM)

Hands-on workshop for distributed training and hosting on SageMaker

Repo contains the code, data and supporting documents including presentations, playbooks and additional documents to support learning

The Corpus & Code for EMNLP 2022 paper "FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correction" | FCGEC中文语法纠错语料及STG模型

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

Implementation of COLING 2024 paper "LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction"

SimPO: Simple Preference Optimization with a Reference-Free Reward

NLP 领域常见任务的实现，包括新词发现、以及基于pytorch的词向量、中文文本分类、实体识别、摘要文本生成、句子相似度判断、三元组抽取、预训练模型等。

Repository for the paper "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop"

Robust recipes to align language models with human and AI preferences

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

A framework for prompt tuning using Intent-based Prompt Calibration

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Bitalostored is a high-performance distributed storage system, core engine based on bitalosdb(self-developed), compatible with Redis protocol.

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

🚀 KIMI AI 长文本大模型逆向API白嫖测试【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、长文档解读、图像OCR、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。

Train transformer language models with reinforcement learning.

Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D…

This repository contains demos I made with the Transformers library by HuggingFace.

An all-in-one LLMs Chat UI for Apple Silicon Mac using MLX Framework.

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

中文大模型能力评测榜单：覆盖百度文心一言、chatgpt、阿里通义千问、讯飞星火、belle / chatglm6b 等开源大模型，多维度能力评测。不仅提供能力评分排行榜，也提供所有模型的原始输出结果！