simonchance
Follow
Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
🚀🚀 「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!
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
Train transformer language models with reinforcement learning.
[ICLR 2025] This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“
💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.
Fine-tuning Qwen2.5-VL for vision-language tasks | Optimized for Vision understanding | LoRA & PEFT support.
A minimal PyTorch re-implementation of Qwen3 VL with a fancy CLI
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
《大模型白盒子构建指南》：一个全手搓的Tiny-Universe
A comprehensive guide to understanding and building Agentic AI systems for beginners
12 Lessons to Get Started Building AI Agents
Happy experimenting with MLLM and LLM models!
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
用 FastAPI 和 Vue3 搭建的 ChatGLM 网页 (前端样式仿照chatgpt-web, 支持chatglm流式输出、前端调整参数、上下文选择、保存图片、知识库问答等功能)
人工精调的中文对话数据集和一段chatglm的微调代码
Repo for Chinese Medical ChatGLM 基于中文医学知识的ChatGLM指令微调
基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
TradingAgents: Multi-Agents LLM Financial Trading Framework
提供一个基于优化lift为目标的决策树搜索工具，可以用于搜索最优阈值、最优策略组合，快速确定拒绝、捞回区域以及提供一些直观的结果输出。该工具主要适用于风控策略场景。