一些 LLM 方面的从零复现笔记
☆243Apr 29, 2025Updated 10 months ago
Alternatives and similar repositories for LLM-from-scratch
Users that are interested in LLM-from-scratch are comparing it to the libraries listed below
Sorting:
- Train a 1B LLM with 1T tokens from scratch by personal☆789Apr 27, 2025Updated 10 months ago
- 用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.☆2,894May 21, 2024Updated last year
- ☆16May 31, 2024Updated last year
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆223Dec 8, 2023Updated 2 years ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆495May 1, 2025Updated 10 months ago
- KuaiSearch PERKS☆12Nov 16, 2021Updated 4 years ago
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆531Mar 23, 2025Updated 11 months ago
- 想要从零开始训练一个中文的mini大语言模型，可以进行基本的对话，模型大小根据手头的机器决定☆65Aug 14, 2024Updated last year
- The implementation for CIKM 2024: Towards Completeness-Oriented Tool Retrieval for Large Language Models.☆24Nov 6, 2024Updated last year
- DETR tensor去除推理过程无用辅助头+fp16部署再次加速+解决转tensorrt 输出全为0问题的新方法。☆12Jan 9, 2024Updated 2 years ago
- Welcome to the LLM Tutorials and RAG Implementations repository! This repository provides tutorials, guides, and implementations for work…☆11Jul 1, 2025Updated 8 months ago
- Created a simple neural network using C++17 standard and the Eigen library that supports both forward and backward propagation.☆10Jul 27, 2024Updated last year
- 中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。☆1,672Apr 20, 2024Updated last year
- 2019年讯飞开发者大赛应用分类标注赛第一名解决方案☆12Oct 23, 2019Updated 6 years ago
- ☆13Jan 22, 2025Updated last year
- chatglm多gpu用deepspeed和☆408Jul 8, 2024Updated last year
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆96Aug 20, 2024Updated last year
- Official repository of Graph RAG-Tool Fusion and ToolLinkOS dataset.☆22Feb 13, 2025Updated last year
- Simple and secure file system mcp server☆21Jun 23, 2025Updated 8 months ago
- 使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力☆161Oct 13, 2025Updated 4 months ago
- 使用单个24G显卡，从0开始训练LLM☆56Jul 9, 2025Updated 7 months ago
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.☆1,094Jul 5, 2025Updated 7 months ago
- ☆313Apr 6, 2023Updated 2 years ago
- baike schema crawler for baidu baike , hudongbaike. 面向百度百科与互动百科的概念分类体系抓取脚本☆38Apr 25, 2018Updated 7 years ago
- 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☆2,777Dec 12, 2023Updated 2 years ago
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆31Feb 26, 2025Updated last year
- ☆148Apr 16, 2024Updated last year
- ⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SF…☆2,408Sep 29, 2023Updated 2 years ago
- ☆64Apr 9, 2024Updated last year
- [ACL 2025] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLM…☆68Oct 27, 2024Updated last year
- [EMNLP 2023] Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models☆17Oct 30, 2023Updated 2 years ago
- 🌟Official code of our AAAI26 paper 🔍WebFilter☆37Nov 9, 2025Updated 3 months ago
- Code for Robust Fine-tuning (RbFT)☆17Jan 31, 2025Updated last year
- This is a python implementation for MACD (moving average convergence/divergence)☆16Feb 4, 2020Updated 6 years ago
- ☆20Nov 3, 2024Updated last year
- 中英文信息抽取数据集整理☆19May 15, 2022Updated 3 years ago
- Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、…☆6,635Oct 24, 2024Updated last year
- 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☆12,546Apr 30, 2025Updated 10 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,037Feb 21, 2026Updated last week