randydl

randydl's Stars

• binary-husky/gpt_academic

  为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

  Language:Python68.1k2801.7k8.3k

• hiyouga/LLaMA-Factory

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

  Language:Python46k2536.4k5.6k

• opendatalab/MinerU

  A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

  Language:Python29.7k1461.2k2.4k

• DS4SD/docling

  Get your documents ready for gen AI

  Language:Python23.9k985261.4k

• HqWu-HITCS/Awesome-Chinese-LLM

  整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

  19.3k241291.9k

• jingyaogong/minimind

  🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

  Language:Python18.3k1312612k

• liguodongiot/llm-action

  本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

  Language:HTML16.1k140271.9k

• HKUDS/LightRAG

  "LightRAG: Simple and Fast Retrieval-Augmented Generation"

  Language:Python13.4k1177281.9k

• FlagOpen/FlagEmbedding

  Retrieval and Retrieval-augmented LLMs

  Language:Python9.2k531.2k660

• EleutherAI/lm-evaluation-harness

  A framework for few-shot evaluation of language models.

  Language:Python8.5k381.3k2.3k

• ymcui/Chinese-LLaMA-Alpaca-2

  中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

  Language:Python7.2k78390575

• wdndev/llm_interview_note

  主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

  Language:HTML6.6k3113747

• PrefectHQ/marvin

  ✨ AI agents that spark joy

  Language:Python5.6k35218360

• lucidrains/x-transformers

  A concise but complete full-attention transformer with a set of promising experimental features from various papers

  Language:Python5.2k56245446

• datawhalechina/so-large-lm

  大模型基础: 一文了解大模型基础知识

  4.5k2732398

• CrazyBoyM/llama3-Chinese-chat

  Llama3、Llama3.1 中文后训练版仓库（微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

  Language:Python4.1k4654340

• shibing624/MedicalGPT

  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、GRPO。

  Language:Python3.8k39422553

• Lightning-AI/LitServe

  Lightning-fast serving engine for any AI model of any size. Flexible. Easy. Enterprise-scale.

  Language:Python3k32128196

• chonkie-ai/chonkie

  🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library

  Language:Python2.9k2158127

• gusye1234/nano-graphrag

  A simple, easy-to-hack GraphRAG implementation

  Language:Python2.7k1895274

• netptop/siteproxy

  reverse proxy, online proxy, 反向代理,免翻墙访问Youtube/twitter/Google, 支持github和telegram web登录(请注意不要通过不信任的代理进行登录)。支持DuckDuckGo AI Chat(可免费访问chatGPT3.5和Claude3)

  Language:JavaScript2.4k401101.2k

• jingyaogong/minimind-v

  🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

  Language:Python2.2k2440230

• ymcui/Chinese-LLaMA-Alpaca-3

  中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

  Language:Python1.9k2181168

• McGill-NLP/llm2vec

  Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

  Language:Python1.5k22137117

• e-p-armstrong/augmentoolkit

  Convert Compute And Books Into Instruct-Tuning Datasets! Makes: QA, RP, Classifiers.

  Language:Python1.4k2368189

• jlesage/docker-baseimage-gui

  A minimal docker baseimage to ease creation of X graphical application containers

  Language:C++1.3k15149192

• multimodal-art-projection/MAP-NEO

  Language:Python933123486

• RICwang/docker-wechat

  在docker里运行wechat，可以通过web或者VNC访问wechat

  Language:Dockerfile74412253

• microsoft/LLM2CLIP

  LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.

  Language:Python498133725

• FlagOpen/FlagData

  Language:Python31541638