Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. 📑 Technical Report | 📖 Blog | 🤗 Hugging Face | 🤖 ModelScope | 💻 GitHub | 🖥️ Demo > [!Note] > This repository contains the model weights and configuration files for Qwen-AgentWorld-35B-A3B, a native language world model trained for agentic environment simulation. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc. Qwen-AgentWorld is the first language world model to cover seven agent interaction domains within a single model. It simulates agentic environments via long chain-of-thought reasoning, predicting the next environment state given an agent’s action and interaction history. Trained through a three-stage pipeline — CPT injects environment knowledge, SFT activates next-state-prediction reasoning, RL sharpens simulation fidelity — Qwen-AgentWorld is a native world model: environment modeling is the training objective from the CPT stage onward, not a post-hoc add-on. — Seven Unified Domains. A single model covers MCP (tool calling), Search, Terminal, SWE (software engineering), Android, Web, and OS — spanning both text and GUI interaction environments. — Native…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: unsloth
Теги: qwen3_5_moe, image-text-to-text, qwen, unsloth, world-model, agent, environment-simulation, conversational
Лайков: 4 | Загрузок: 196
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
