bodhibudd

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

LaTeX_OCR

:gem: 数学公式识别 Math Formula OCR

haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

open-parse

Improved file parsing for LLM’s

pdf-struct

Logical structure analysis for visually structured documents

fastRAG

Efficient Retrieval Augmentation and Generation Framework

natural-instructions

Expanding natural instructions

pdf2png

将pdf转换成png图片

MediaCrawler

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫

baidu_baike

MoZi

首个全参数训练的知识产权大模型 MoZi (墨子)

OpenDevin

🐚 OpenDevin: Code Less, Make More

DISC-FinLLM

DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financial consulting services in financial scenarios.

awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

ChatGLM-Finetuning

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

Chinese-Mixtral-8x7B

中文Mixtral-8x7B（Chinese-Mixtral-8x7B）

LLamaTuner

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

GoGPT

GoGPT:基于Llama/Llama 2训练的中英文增强大模型|Chinese-Llama2

Baichuan2

A series of large language models developed by Baichuan Intelligent Technology

Bert-Chinese-Text-Classification-Pytorch

使用Bert，ERNIE，进行中文文本分类

EditScorer

The code for EMNLP2022 paper "Improved grammatical error correction by ranking elementary edits"

LaWGPT

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

memory-efficient-attention-pytorch

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

Firefly

Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

bytepiece

更纯粹、更高压缩率的Tokenizer

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

DISC-LawLLM

DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services

sentence_segmentation_dl