ScienceOne-AI / DeepSeek-671B-SFT-GuideLinks
An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案,包含从训练到推理的完整代码和脚本,以及实践中积累一些经验和结论。)
☆703Updated 3 months ago
Alternatives and similar repositories for DeepSeek-671B-SFT-Guide
Users that are interested in DeepSeek-671B-SFT-Guide are comparing it to the libraries listed below
Sorting:
- 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。☆437Updated 4 months ago
- DeepSeek 系列工作解读、扩展和复现。☆658Updated 2 months ago
- ☆717Updated 3 weeks ago
- ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents☆500Updated 2 weeks ago
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆782Updated this week
- Train a 1B LLM with 1T tokens from scratch by personal☆679Updated last month
- Building DeepSeek R1 from Scratch☆630Updated 3 months ago
- 🌐 WebWalker [ACL2025] & WebDancer [Preprint]☆1,069Updated 2 weeks 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。👩🎓👨🎓☆781Updated this week
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆1,203Updated this week
- minimal-cost for training 0.5B R1-Zero☆743Updated last month
- ☆954Updated last month
- This is a user guide for the MiniCPM and MiniCPM-V series of small language models (SLMs) developed by ModelBest. “面壁小钢炮” focuses on achi…☆247Updated 7 months ago
- 从零实现一个小参数量中文大语言模型。☆709Updated 10 months ago
- [ACL 2025 Demo] Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths☆487Updated last month
- Community maintained hardware plugin for vLLM on Ascend☆791Updated this week
- Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent☆341Updated 2 months ago
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,147Updated this week
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,130Updated 2 months ago
- Distributed RL System for LLM Reasoning☆1,837Updated this week
- Awesome LLM pre-training resources, including data, frameworks, and methods.☆180Updated last month
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆441Updated last month
- Reproduce R1 Zero on Logic Puzzle☆2,361Updated 3 months ago
- 大模型算法岗面试题(含答案):常见问题和概念解析 "大模型面试题"、"算法岗面试"、"面试常见问题"、"大模型算法面试"、"大模型应用基础"☆992Updated this week
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆2,764Updated this week
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆444Updated 3 months ago
- Collect every awesome work about r1!☆388Updated last month
- 复现大模型相关算法及一些学习记录☆1,739Updated last week
- LLMs-from-scratch项目中文翻译☆1,172Updated 2 months ago
- A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.☆816Updated last week