StudyingLover / llm-pydantic-openai-json
调用大模型已经是如今做 ai 项目习以为常的工作的，但是大模型的输出很多时候是不可控的，我们又需要使用大模型去做各种下游任务，实现可控可解析的输出。我们探索了一种和 python 开发可以紧密合作的开发方法。
☆11Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for llm-pydantic-openai-json
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆44Updated 5 months ago
- LLM+RAG for QA☆19Updated 9 months ago
- 通义千问的DPO训练☆27Updated last month
- the newest version of llama3，source code explained line by line using Chinese☆22Updated 6 months ago
- 中文海事大模型郑和（Zh-LLM）☆13Updated 10 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+☆73Updated 10 months ago
- Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案☆71Updated last week
- 可以成功Lora微调的Qwen-VL模型☆16Updated last year
- ☆21Updated 3 months ago
- Here is a demo for PDF parser (Including OCR, object detection tools)☆31Updated last month
- 用于AIOPS24挑战赛的Demo☆57Updated 4 months ago
- Xtuner Factory☆31Updated 8 months ago
- 快速入门RAG与私有化部署☆129Updated 6 months ago
- ☆15Updated 4 months ago
- AI 应用示例合集☆68Updated 5 months ago
- ☆21Updated last month
- LLM Tokenizer with BPE algorithm☆27Updated 6 months ago
- Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".☆50Updated 3 months ago
- 基于BM25、BGE的检索增强生成RAG示例☆97Updated 2 weeks ago
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆26Updated 5 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
- 中文领域心理健康对话大模型simpsybot☆16Updated 2 weeks ago
- 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！☆13Updated 3 months ago
- 补充了一些Visualglm缺少的文件，可以对Visualglm进行训练，实例中是对人脸做了面相的识别☆12Updated last year
- ☆88Updated 4 months ago
- A minimalist benchmarking tool designed to test the routine-generation capabilities of LLMs.☆15Updated last week
- 用VLLM框架部署千问1.5并进行流式输出☆22Updated 6 months ago
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated 7 months ago
- TianGong-AI-Unstructure☆51Updated this week