zhanshijinwat / Steel-LLMLinks
Train a 1B LLM with 1T tokens from scratch by personal
☆663Updated last month
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.☆435Updated last month
- 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。☆408Updated 3 months ago
- 开源SFT数据集整理,随时补充☆516Updated 2 years ago
- 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。☆325Updated 10 months ago
- 一些 LLM 方面的从零复现笔记☆200Updated last month
- 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.☆552Updated 10 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。👩🎓👨🎓☆756Updated 2 weeks ago
- 从0开始,将chatgpt的技术路线跑一遍。☆237Updated 8 months ago
- DeepSeek 系列工作解读、扩展和复现。☆652Updated 2 months ago
- 从零实现一个小参数量中文大语言模型。☆665Updated 9 months ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆389Updated 9 months ago
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆439Updated 2 months ago
- personal chatgpt☆372Updated 5 months ago
- 通义千问VLLM推理部署DEMO☆580Updated last year
- 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☆543Updated last year
- minimal-cost for training 0.5B R1-Zero☆730Updated 2 weeks ago
- ☆931Updated 3 weeks ago
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆1,076Updated this week
- Real-time updated, fine-grained reading list on LLM-synthetic-data.🔥☆257Updated 4 months ago
- ☆328Updated 11 months ago
- ☆706Updated this week
- Reproduce R1 Zero on Logic Puzzle☆2,347Updated 2 months ago
- TinyRAG☆297Updated 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)☆333Updated last year
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆999Updated last year
- 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☆410Updated last year
- CMMLU: Measuring massive multitask language understanding in Chinese☆763Updated 5 months ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,113Updated this week
- 本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.☆257Updated 5 months ago
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,076Updated 2 months ago