pydaxing / clip_blip_embedding_rag
在RAG技术中,嵌入向量的生成和匹配是关键环节。本文介绍了一种基于CLIP/BLIP模型的嵌入服务,该服务支持文本和图像的嵌入生成与相似度计算,为多模态信息检索提供了基础能力。
☆10Updated 3 weeks ago
Alternatives and similar repositories for clip_blip_embedding_rag:
Users that are interested in clip_blip_embedding_rag are comparing it to the libraries listed below
- 可以成功Lora微调的Qwen-VL模型☆18Updated last year
- Bert TensorRT模型加速部署☆9Updated 2 years ago
- ChatGLM2-6B-Explained☆34Updated last year
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆45Updated 7 months ago
- baichuan and baichuan2 finetuning and alpaca finetuning☆32Updated 8 months ago
- BLOOM 模型的指令微调☆24Updated last year
- This project is mainly to explore what effect can be achieved by fine-tuning LLM model (ChatGLM-6B)of about 6B in vertical field (Romance…☆25Updated last year
- 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答, 75+ baseline☆56Updated last year
- 一套代码指令微调大模型☆37Updated last year
- 纯c++的全平台llm加速库,支持python调用,支持baichuan, glm, llama, moss基座,手机端流畅运行chatglm-6B级模型单卡可达10000+token / s,☆45Updated last year
- 基于internlm-chat-7b的保险知识大模型微调☆13Updated 8 months ago
- 基于lora微调Qwen1.8chat的实战教程☆24Updated 3 months ago
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答 baseline 80+☆83Updated last year
- Tracking the hot Github repos and update daily 每天自动追踪Github热门项目☆44Updated this week
- Recursive Abstractive Processing for Tree-Organized Retrieval☆11Updated 7 months ago
- ☆90Updated last year
- share data, prompt data , pretraining data☆35Updated last year
- ☆22Updated last year
- Here is a demo for PDF parser (Including OCR, object detection tools)☆31Updated 3 months ago
- 基于Qwen2模型进行通用信息抽取【实体/关系/事件抽取】☆29Updated 6 months ago
- deep training task☆29Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆105Updated last year
- prompt engineering ,llm,text2sql☆34Updated last year
- 千问14B和7B的逐行解释☆53Updated last year
- Finetune baichuan pretrained model with QLora method☆15Updated last year
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆54Updated last year
- ☆14Updated last year
- Legal-Eagle-InternLM 是一个基于商汤科技和上海人工智能实验室推出的书生浦语大模型InternLM的法律问答机器人。旨在为用户提供符合3H(即Helpful、Honest、Harmless)原则的专业、智能、全面的法律服务的法律领域大模型。☆50Updated 10 months ago
- 学习开源chatGPT类模型的指南,汇总各种训练数据获取、模型微调、模 型服务的方法,以及记录自己操作总遇到的各种常见坑,欢迎收藏、转发,希望能帮你省一些时间☆70Updated last year