RethinkFun / trian_ppoLinks
☆124Updated last year
Alternatives and similar repositories for trian_ppo
Users that are interested in trian_ppo are comparing it to the libraries listed below
Sorting:
- ☆115Updated last year
- 主要记录大语言大模型(LLMs) 算法(应用)工程师多模态相关知识☆250Updated last year
- llm & rl☆243Updated 3 weeks ago
- ☆103Updated 5 months 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。☆76Updated last year
- ☆396Updated 9 months ago
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆127Updated last year
- personal chatgpt☆389Updated 11 months ago
- 通义千问的DPO训练☆58Updated last year
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆180Updated 2 years ago
- Qwen2.5 0.5B GRPO☆71Updated 9 months ago
- LLM Tokenizer with BPE algorithm☆44Updated last year
- 一些 LLM 方面的从零复现笔记☆236Updated 6 months ago
- 将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调☆426Updated 2 months ago
- 一些大语言模型和多模态模型的生态,主要包括跨模态搜索、投机解码、QAT量化、多模态量化、ChatBot、OCR☆193Updated 3 months ago
- Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...☆79Updated 6 months ago
- ☆58Updated last year
- 《多模态大模型:新一代人工智能技术范式》作者:刘阳,林倞☆249Updated 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。👩🎓👨🎓☆895Updated this week
- Train a 1B LLM with 1T tokens from scratch by personal☆751Updated 6 months ago
- ☆85Updated 9 months ago
- LLM大模型(重点)以及搜广推等 AI 算法中手写的面试题,(非 LeetCode),比如 Self-Attention, AUC等,一般比 LeetCode 更考察一个人的综合能力,又更贴近业务和基础知识一点☆434Updated 10 months ago
- Inference code for LLaMA models☆127Updated 2 years ago
- 包含程序员面试大厂面试题和面试经验☆193Updated 5 months ago
- ☆141Updated 3 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆266Updated last year
- ☆19Updated last year
- 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。☆670Updated 8 months ago
- from MHA, MQA, GQA to MLA by 苏剑林, with code☆33Updated 8 months ago
- 一个很小很小的RAG系统☆309Updated 6 months ago