shell-nlp / gpt_server
gpt_server是一个用于生产级部署LLMs或Embedding的开源框架。
☆120Updated this week
Related projects ⓘ
Alternatives and complementary repositories for gpt_server
- A high-throughput and memory-efficient inference and serving engine for LLMs☆121Updated 10 months ago
- 部署你自己的OpenAI api🤩, 基于flask, transformers (使用 Baichuan2-13B-Chat-4bits 模型, 可以运行在单张Tesla T4显卡) ,实现了OpenAI中Chat, Models和Completions接口,包含流式响…☆84Updated 11 months ago
- 360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute☆234Updated last month
- Imitate OpenAI with Local Models☆85Updated 2 months ago
- Alpaca Chinese Dataset -- 中文指令微调数据集【人工+GPT4o持续更新】☆184Updated last month
- 中文原生检索增强生成测评基准☆98Updated 6 months ago
- ChatGPT WebUI using gradio. 给 LLM 对话和检索知识问答RAG提供一个简单好用的Web UI界面☆93Updated 2 months ago
- Implement OpenAI APIs and plugin-enabled ChatGPT with open source LLM and other models.☆122Updated 4 months ago
- Easy, fast, and cheap pretrain,finetune, serving for everyone☆259Updated this week
- 基于BM25、BGE的检索增强生成RAG示例☆96Updated last week
- 大语言模型指令调优工具(支持 FlashAttention)☆166Updated 10 months ago
- bge推理优化相关脚本☆24Updated 9 months ago
- Agentica: Build Multi-Agent Workflow with 3 lines code. 三行代码打造个人助手智能体。☆85Updated 3 weeks ago
- ☆56Updated 2 weeks ago
- 首个llama2 13b 中文版模型 (Base + 中文对话SFT,实现流畅多轮人机自然语言交互)☆89Updated last year
- ☆105Updated last year
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆231Updated this week
- An easy-to-use framework for modular RAG☆289Updated this week
- ☆59Updated last month
- Analysis of Chinese and English layouts 中英文版面分析☆121Updated 3 weeks ago
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆166Updated 5 months ago
- 添加🚀流式 Web 服务到 GraphRAG,兼容 OpenAI SDK,支持可访问的实体链接🔗,支持建议问题,兼容本地嵌入模型,修复诸多问题。Add streaming web server to GraphRAG, compatible with OpenAI SD…☆187Updated this week
- ☆213Updated 5 months ago
- (1)弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练,提高万级tokens性能支持。(2)证据理论解释学习,提升模型的复杂逻辑推理能力(3)兼容alpaca数据格式。☆45Updated last year
- chatglm2 6b finetuning and alpaca finetuning☆144Updated 6 months ago
- 用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.☆241Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆209Updated last year
- code for piccolo embedding model from SenseTime☆106Updated 5 months ago
- SmartSearch: Building a quick conversation-based search engine with LLMs.☆42Updated 6 months ago
- SMP 2023 ChatGLM金融大模型挑战赛 60 分baseline思路介绍☆182Updated last year