PyTorch native post-training library
Repository Index
98,836 visible repositories in the index
25–48 of 108 · Most stars
Train the smallest LM you can that fits in 16MB. Best model wins!
This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.
- academic-writing
- ai-writing
- chatgpt
- chatgpt-prompts
Set of tools to assess and improve LLM security.
The Apache Tika toolkit detects and extracts metadata and text from over a thousand different file types (such as PPT, XLS, and PDF).
- java
- tika
- metadata
- extraction
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁,一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭建后端🗝️、Docker-compose 打包部署🐋
- chat-application
- internlm-chat-7b
- internlm2
- llm
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
- security-tools
- agent-ai-cli
- agent-security
- mobile-device-management
Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
A high-performance inference engine for AI models
把你在各处注册的 New API / One API / OneHub / DoneHub / Veloera / AnyRouter / Sub2API 等站点, 汇聚成 一个 API Key、一个入口,自动发现模型、智能路由、成本最优
Comet: agent skill harness for turning ideas into evaluated workflows
Same agent, Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
- observability
- llmops
- ai-observability
- openai
AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge across 100+ apps while keeping data secure. Deploy in minutes, not months.
- search
- search-engine
- federated-query
- federated-search
NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
- machine-learning
- pascal-voc
- average-precision
- ground-truth
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- proof-assistant
- lean4
- ai-agents
- ai-for-math
A Unified Library for Parameter-Efficient and Modular Transfer Learning
- nlp
- natural-language-processing
- adapters
- transformers
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台,我们欢迎开源爱好者发起任何有意义的pr!
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
- evaluation
- evaluation-framework
- evaluation-metrics
- huggingface
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
- finetune
- stable-diffusion