UnicomAI / UniT2IXLLinks
☆59Updated 7 months ago
Alternatives and similar repositories for UniT2IXL
Users that are interested in UniT2IXL are comparing it to the libraries listed below
Sorting:
- Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM☆101Updated last year
- 将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调☆226Updated last week
- hf-mirror-cli 使用国内镜像，无需配置开箱即用，快速下载hugingface上的模型☆141Updated 6 months ago
- ☆173Updated 6 months ago
- ☆350Updated last year
- ☆325Updated 2 weeks ago
- Python3 package for Chinese/English OCR,use paddleocr-v5 onnx model(~20MB), with ultra-fast inference speed. 基于ppocr-v5-onnx模型推理，中英文OCR开源…☆95Updated 3 weeks ago
- Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.☆245Updated 5 months ago
- ☆235Updated 5 months ago
- ☆80Updated last year
- Taiyi-Diffusion-XL训练代码☆23Updated last year
- 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力，接近gpt4o、claude-3.5-sonnet的识别水平！☆24Updated last year
- 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☆186Updated 2 weeks ago
- 集成了LLM与SDXL的AIGC应用程序☆29Updated last year
- Phi3 中文后训练模型仓库☆321Updated 8 months ago
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆56Updated 8 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。☆64Updated 11 months ago
- [ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval☆212Updated 2 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆41Updated 3 weeks ago
- GLM Series Edge Models☆147Updated 2 months ago
- 中文文生图stable diffsion模型集合☆351Updated this week
- 研究GOT-OCR-项目落地加速，不限语言☆61Updated 9 months ago
- 视频分类标注、视频时空标注☆41Updated last year
- 支持中英文双语视觉-文本对话的开源可商用多模态模型。☆374Updated last year
- 视频理解：千问视频多模态模型 & Dify☆63Updated 11 months ago
- Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。☆295Updated last year
- ☆79Updated 2 years ago
- 从零到一实现了一个多模态大模型，并命名为Reyes（睿视），R：睿，eyes：眼。Reyes的参数量为8B，视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct，Reyes也通过一个两层MLP投影层连…☆22Updated 5 months ago
- 360zhinao☆291Updated 2 months ago
- ☆65Updated last year