zhanshijinwat / Steel-LLMLinks
Train a 1B LLM with 1T tokens from scratch by personal
☆740Updated 5 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.☆474Updated 5 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。☆645Updated 8 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆264Updated last year
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆344Updated last year
- 一些 LLM 方面的从零复现笔记☆226Updated 5 months ago
- 开源SFT数据集整理,随时补充☆547Updated 2 years ago
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆490Updated 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.☆573Updated last year
- DeepSeek 系列工作解读、扩展和复现。☆681Updated 6 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。👩🎓👨🎓☆885Updated this week
- LLMs interview notes and answers:该仓库主要记录大模 型(LLMs)算法工程师相关的面试题和参考答案☆599Updated 2 years ago
- personal chatgpt☆386Updated 10 months ago
- 从零实现一个小参数量中文大语言模型。☆856Updated last year
- 通义千问VLLM推理部署DEMO☆611Updated last year
- TinyRAG☆350Updated 3 months ago
- ☆748Updated last month
- Reproduce R1 Zero on Logic Puzzle☆2,407Updated 7 months ago
- ☆1,080Updated last month
- 该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记(多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT)☆359Updated last year
- A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.☆844Updated 4 months ago
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆120Updated last year
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.☆1,047Updated 3 months ago
- minimal-cost for training 0.5B R1-Zero☆778Updated 5 months ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆414Updated last year
- ☆964Updated 8 months ago
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,401Updated 2 months ago
- FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目,基于大模型搭建金融场景智能问答系统,利用开源开放来促进「AI+金融」。☆412Updated last year
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆1,016Updated last year
- YuLan: An Open-Source Large Language Model☆633Updated 9 months ago
- ☆84Updated 8 months ago