hellangleZ / Qwen3_autothink_adapterLinks
Implemented a script that automatically adjusts Qwen3's inference and non-inference capabilities, based on an OpenAI-like API. The inference framework can be sglang, or it can be adapted/modified to use vLLM
☆22Updated 5 months ago
Alternatives and similar repositories for Qwen3_autothink_adapter
Users that are interested in Qwen3_autothink_adapter are comparing it to the libraries listed below
Sorting:
- support BM25+vecetor☆29Updated 4 months ago
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆21Updated last year
- Auto Thinking Mode switch for Qwen3 in Open webui☆68Updated 5 months ago
- REFRAG-style RAG (compress → sense/select → expand) — Single-file reference implementation☆103Updated 3 weeks ago
- Bambo is a new proxy framework. Compared with mainstream frameworks, it is more lightweight and flexible and can handle various load task…☆34Updated 8 months ago
- 大模型智能体Agent中文教程,博客代码仓库☆44Updated 2 weeks ago
- Lighter, cheaper and faster RAG toolkit (Graph RAG) supported by TargetPilot☆46Updated 4 months ago
- MCP DeepResearch Server: 基于 LangGraph + Ollama + Tavily 的深度研究服务器,支持异步运行、超时控制与进度推送☆31Updated 4 months ago
- 最简易的R1结果在小模型上的复现,阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证,对于强推理能力,think思考过程性内容是AGI/ASI的核心。☆45Updated 8 months ago
- A lightweight script for processing HTML page to markdown format with support for code blocks☆80Updated last year
- AgileGen: Empowering Agile-Based Generative Software Development through Human-AI Teamwork (accepted by ACM TOSEM)☆23Updated 11 months ago
- diagnosis_zero, R1 Zero reproduce on disease diagnosis☆32Updated 3 months ago
- Evaluation for AI apps and agent☆43Updated last year
- ☆16Updated 3 months ago
- Try out HallOumi, a state-of-the-art claim verification model in a simple UI!☆41Updated 6 months ago
- Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"☆146Updated 4 months ago
- The code for paper: Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search☆59Updated 3 months ago
- DeepSearch Code-Actions Agent (DSCA). Build 🙌 with 🤗 smolagents☆123Updated 2 months ago
- agentcp是一个基于ACP协议的Agent sdk,用于解决Agent间的身份认证及通信问题;用于创建AID、连接入网、构建会话,收发消息等;支持多Agent协作,异步消息处理,支持内网穿透,支持Agent访问的负载均衡☆15Updated 3 months ago
- An open-source chat text to control actions agentic workflow framework/showcase powered by Agently AI application development framework.☆28Updated last year
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆41Updated last year
- Open replication of DeepSeek R1 for text-to-graph extraction.☆99Updated 8 months ago
- ☆95Updated 10 months ago
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆197Updated this week
- Official repository for RAGViz: Diagnose and Visualize Retrieval-Augmented Generation [EMNLP 2024]☆85Updated 9 months ago
- Enable tool-use ability for any LLM model (DeepSeek V3/R1, etc.)☆57Updated 4 months ago
- Qwen GRPO Graph Extraction RL Finetune☆57Updated 6 months ago
- xllamacpp - a Python wrapper of llama.cpp☆60Updated last week
- Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".☆71Updated last year
- Implementing ReaRAG, a knowledge-guided reasoning model that enhances factual accuracy using iterative retrieval-augmented generation. Ad…☆15Updated 6 months ago