jingyaogong / minimind
🚀🚀 「大模型」3小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 3 hours!
☆4,984Updated last month
Alternatives and similar repositories for minimind:
Users that are interested in minimind are comparing it to the libraries listed below
- 🚀 「大模型」3小时从0训练27M参数的视觉多模态VLM！🌏 Train a 27M-parameter VLM from scratch in just 3 hours!☆653Updated last month
- Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.☆5,320Updated this week
- MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.☆7,066Updated 2 months ago
- MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone☆13,445Updated this week
- An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)☆4,158Updated this week
- 🧑🚀 全世界最好的LLM资料总结 | Summary of the world's best LLM resources.☆2,949Updated this week
- GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型☆5,730Updated 2 weeks ago
- KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning a…☆4,258Updated this week
- 🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)☆5,719Updated last week
- Llama3、Llama3.1 中文仓库（随书籍撰写中... 各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）☆4,115Updated 4 months ago
- [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型☆6,793Updated 3 weeks ago
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,035Updated 3 months ago
- Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek3, ...) and 150+…☆5,069Updated this week
- 中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。☆1,351Updated 8 months ago
- Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、…☆6,019Updated 2 months ago
- 用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.☆2,623Updated 7 months ago
- Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model☆6,576Updated this week
- 《大模型白盒子构建指南》：一个全手搓的Tiny-Universe☆1,941Updated 3 weeks ago
- Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization☆3,791Updated 3 weeks ago
- 中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3☆1,825Updated 3 months ago
- Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you ne…☆5,961Updated this week
- Using GPT to parse PDF☆3,175Updated 5 months ago
- TEN Agent is a conversational AI powered by the TEN, integrating Gemini 2.0 Live, OpenAI Realtime, RTC, and more. It delivers real-time c…☆3,897Updated this week
- ☆1,353Updated last month
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆4,496Updated last week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆38,227Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆5,169Updated this week
- GLM-4-Voice | 端到端中英语音对话模型☆2,565Updated last month
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆2,372Updated this week
- Retrieval and Retrieval-augmented LLMs☆8,237Updated this week