[ICLR-2025-SLLM Spotlight 🔥]MobiLlama : Small Language Model tailored for edge devices
- efficient-llm
- llm
- slm
- mobile-llm
132,241 visible repositories in the index
1,801–1,824 of 2,139 · Most stars
[ICLR-2025-SLLM Spotlight 🔥]MobiLlama : Small Language Model tailored for edge devices
Build agent that uses 80% less token and delivers better results.
PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning
AI agent skills for social media content strategy, creation, and analysis across text-first platforms
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.
A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.
Agent skill for color science expertise. Many references covering color spaces, accessibility (APCA, WCAG), palette generation, pigment mixing, and historical color theory. Works with Claude Code, Codex, Cursor, Copilot & others.
Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, no middleman.
A personal wearable AI that runs locally
Best practice for training LLaMA models in Megatron-LM
🤖💬 AI SDK, extra small.
Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]
This is the official github repo of Think-on-Graph (ICLR 2024). If you are interested in our work or willing to join our research team in Shenzhen, please feel free to contact us by email ([email protected])
RAT is a powerful tool that improves AI responses by leveraging DeepSeek's reasoning capabilities to guide other models through a structured thinking process.
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
基于Golang/go-zero的AIoT物联网平台与SaaS开发底座,融合AI智能体、RAG知识库、记忆和工具调用。支持多租户、多应用、项目管理、设备管理、物模型、场景联动、告警、组态及3D数字孪生。提供MQTT/CoAP/HTTP/TCP接入及阿里云、腾讯云、涂鸦云对接,支持MySQL/PostgreSQL。借助Skills/CLI快速开发,适用于智慧能源、楼宇、停车、家居、农业与工业。
Governance standard and reference toolset for LLM-maintained knowledge corpora
The unofficial OpenAI SDK for Dart & Flutter. Full API coverage + OpenAI-compatible providers (Azure, DeepSeek, LM Studio, Ollama): Responses, Chat, Realtime, Videos, Batch, Fine-tuning.
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models
Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.
Cell type annotation for single-cell RNA-seq using multi-LLM consensus