从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)
☆552Mar 23, 2025Updated last year
Alternatives and similar repositories for build_MiniLLM_from_scratch
Users that are interested in build_MiniLLM_from_scratch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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.☆2,923May 21, 2024Updated 2 years ago
- 从0开始，将chatgpt的技术路线跑一遍。☆281Sep 5, 2024Updated last year
- 从零到一实现一个 miniLLM～（动手学习LLM）☆80May 4, 2026Updated 2 months ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆503May 1, 2025Updated 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。☆1,725Apr 20, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 从零实现一个小参数量中文大语言模型。☆1,071Aug 22, 2024Updated last year
- 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☆66Aug 14, 2024Updated last year
- Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.☆591Jul 11, 2024Updated 2 years ago
- 训练一个对中文支持更好的LLaVA模型，并开源训练代码和数据。☆82Sep 6, 2024Updated last year
- An elegent pytorch implement of transformers☆1,328May 16, 2026Updated 2 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆812Apr 27, 2025Updated last year
- Inference Llama/Llama2/Llama3 Modes in NumPy☆21Nov 22, 2023Updated 2 years ago
- 仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理☆4,288Mar 26, 2026Updated 4 months ago
- 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）☆24,813Jul 19, 2026Updated last week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.☆847Jun 16, 2025Updated last year
- 目标：构建一个更符合语言学的小而美的 llama 分词器，支持中英日三国语言☆19Jun 2, 2024Updated 2 years ago
- 一些 LLM 方面的从零复现笔记☆256Apr 29, 2025Updated last year
- 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。☆22,701May 10, 2026Updated 2 months ago
- 利用Torch和强化学习训练flappy bird小游戏☆13Nov 18, 2022Updated 3 years ago
- 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!☆53,904Updated this week
- 《大模型白盒子构建指南》：一个全手搓的Tiny-Universe☆4,987Feb 12, 2026Updated 5 months ago
- 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。☆5,667Jun 3, 2026Updated last month
- 一个适合学习、使用、自主扩展的RAG【检索增强生成】系统！可联网做AI搜索☆525Sep 4, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 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☆14,770Jun 14, 2026Updated last month
- tutorial for writing custom pytorch cpp+cuda kernel, applied on volume rendering (NeRF)☆29Dec 12, 2023Updated 2 years ago
- 集成学习思维导图☆21Apr 6, 2023Updated 3 years ago
- 👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!☆8,374Jun 28, 2026Updated last month
- 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程☆31,461Jul 15, 2026Updated 2 weeks ago
- 中文nlp解决方案(大模型、数据、模型、训练、推理)☆3,833Aug 5, 2025Updated 11 months 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、…☆6,649Oct 24, 2024Updated last year
- 😜 表情包视觉数据集，使用glm-4v、step-1v的图像解析能力标注。☆149Apr 27, 2024Updated 2 years ago
- Alpaca Chinese Dataset -- 中文指令微调数据集☆220Oct 6, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆73,582Updated this week
- macrogpt大模型全量预训练(1b3,32层), 多卡deepspeed/单卡adafactor☆15Nov 30, 2023Updated 2 years ago
- 本项目致力于为大模型领域的初学者提供全面的知识体系，包括基础和高阶内容，以便开发者能迅速掌握大模型技术栈并全面了解相关知识。☆64Jan 6, 2025Updated last year
- Rust implementation of Surya☆66Mar 1, 2025Updated last year
- 使用单个24G显卡，从0开始训练LLM☆54Jul 9, 2025Updated last year
- 大模型基础: 一文了解大模型基础知识☆7,515Jun 22, 2026Updated last month
- Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆415Oct 21, 2023Updated 2 years ago