Train a 1B LLM with 1T tokens from scratch by personal
☆789Apr 27, 2025Updated 10 months ago
Alternatives and similar repositories for Steel-LLM
Users that are interested in Steel-LLM are comparing it to the libraries listed below
Sorting:
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆495May 1, 2025Updated 10 months ago
- 这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。☆773Feb 18, 2025Updated last year
- 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.☆2,895May 21, 2024Updated last year
- ☆979Feb 7, 2025Updated last year
- ☆235May 10, 2024Updated last year
- Reproduce R1 Zero on Logic Puzzle☆2,440Mar 20, 2025Updated 11 months ago
- Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷☆6,001Updated this week
- 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。☆1,675Apr 20, 2024Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,084Updated this week
- minimal-cost for training 0.5B R1-Zero☆809May 14, 2025Updated 9 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、…☆6,638Oct 24, 2024Updated last year
- 一些 LLM 方面的从零复现笔记☆244Apr 29, 2025Updated 10 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）☆23,400Mar 1, 2026Updated last week
- 中文nlp解决方案(大模型、数据、模型、训练、推理)☆3,782Aug 5, 2025Updated 7 months ago
- 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.☆584Jul 11, 2024Updated last year
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.☆1,100Jul 5, 2025Updated 8 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, …☆12,956Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,902May 3, 2024Updated last year
- 从0开始，将chatgpt的技术路线跑一遍。☆272Sep 5, 2024Updated last year
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,705Feb 27, 2026Updated last week
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆224Jul 25, 2025Updated 7 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。☆4,862Feb 10, 2026Updated 3 weeks ago
- Simple RL training for reasoning☆3,830Dec 23, 2025Updated 2 months ago
- A Next-Generation Training Engine Built for Ultra-Large MoE Models☆5,092Updated this week
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Apr 12, 2024Updated last year
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆67,966Updated this week
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,681Feb 26, 2026Updated last week
- ⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SF…☆2,409Sep 29, 2023Updated 2 years ago
- Retrieval and Retrieval-augmented LLMs☆11,352Dec 15, 2025Updated 2 months ago
- DeepSeek 系列工作解读、扩展和复现。☆699Mar 29, 2025Updated 11 months ago
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆533Mar 23, 2025Updated 11 months ago
- 欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主 流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩🎓👨🎓☆929Dec 1, 2025Updated 3 months ago
- 从零实现一个小参数量中文大语言模型。☆957Aug 22, 2024Updated last year
- Modeling, training, eval, and inference code for OLMo☆6,353Nov 24, 2025Updated 3 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,519Mar 2, 2026Updated last week
- 🚀🚀 「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!☆40,273Feb 6, 2026Updated last month
- BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）☆8,283Oct 16, 2024Updated last year
- 怎么训练一个LLM分词器☆153Jul 13, 2023Updated 2 years ago
- Fully open reproduction of DeepSeek-R1☆25,927Nov 24, 2025Updated 3 months ago