OpenBMB / MiniCPM-VLinks
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
☆22,023Updated 2 weeks ago
Alternatives and similar repositories for MiniCPM-V
Users that are interested in MiniCPM-V are comparing it to the libraries listed below
Sorting:
- MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks☆8,375Updated last week
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆13,594Updated this week
- [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☆9,289Updated 2 weeks ago
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆11,838Updated last week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,940Updated last year
- Mobile-Agent: The Powerful GUI Agent Family☆5,944Updated last week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆59,732Updated this week
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆24,917Updated last week
- Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model☆7,888Updated 7 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆59,413Updated this week
- The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.☆6,274Updated last year
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,565Updated 8 months ago
- Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.☆46,548Updated this week
- 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…☆8,596Updated last week
- [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"☆21,534Updated this week
- 🚀🚀 「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!☆26,994Updated 5 months ago
- A simple screen parsing tool towards pure vision based GUI agent☆23,622Updated 3 weeks ago
- Enjoy the magic of Diffusion models!☆10,232Updated last week
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆19,438Updated last week
- The official Meta Llama 3 GitHub site☆28,998Updated 8 months ago
- Retrieval and Retrieval-augmented LLMs☆10,621Updated 2 weeks ago
- Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚☆31,644Updated 6 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆18,662Updated this week
- DeepSeek Coder: Let the Code Write Itself☆22,189Updated last year
- RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to creat…☆65,563Updated this week
- DeepSeek-VL: Towards Real-World Vision-Language Understanding☆3,964Updated last year
- open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming…☆3,417Updated 11 months ago
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audi…☆8,960Updated last week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (…☆10,209Updated this week
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆23,663Updated last year