QwenLM / Qwen3GuardLinks
Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.
☆232Updated this week
Alternatives and similar repositories for Qwen3Guard
Users that are interested in Qwen3Guard are comparing it to the libraries listed below
Sorting:
- ☆293Updated 4 months ago
- Implementation for OAgents: An Empirical Study of Building Effective Agents☆262Updated last month
- Data Synthesis for Deep Research Based on Semi-Structured Data☆165Updated last week
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆159Updated 2 weeks ago
- MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.☆387Updated this week
- ☆91Updated 4 months ago
- (ICCV 2025) OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation☆87Updated 3 months ago
- ☆84Updated 5 months ago
- LIMI: Less is More for Agency☆69Updated last week
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents☆406Updated last month
- Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"☆155Updated last month
- Complex Function Calling Benchmark.☆135Updated 8 months ago
- SSRL: Self-Search Reinforcement Learning☆145Updated last month
- [EMNLP 2024] OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs.☆148Updated 10 months ago
- Code that accompanies the public release of the paper Lost in Conversation (https://arxiv.org/abs/2505.06120)☆171Updated 3 months ago
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆217Updated 2 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆343Updated 3 months ago
- Official repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs".☆240Updated last year
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆253Updated last week
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆260Updated last year
- Official code repository for Sketch-of-Thought (SoT)☆127Updated 4 months ago
- The All-in-one Judge Models introduced by Opencompass☆114Updated 2 months ago
- ☆131Updated this week
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆245Updated 4 months ago
- ☆101Updated 4 months ago
- Tina: Tiny Reasoning Models via LoRA☆284Updated last week
- RetroLLM: Empowering LLMs to Retrieve Fine-grained Evidence within Generation [ACL 2025]☆117Updated 8 months ago
- Beating the GAIA benchmark with Transformers Agents. 🚀☆136Updated 7 months ago
- ☆320Updated last year
- Prompt-to-Leaderboard☆256Updated 4 months ago