view post Post 4155 You can now train your own Decision model like Jev locally!We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.GitHub: https://github.com/unslothai/unslothGuide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth See translation 4 replies · ❤️ 17 17 🔥 8 8 👍 4 4 ➕ 2 2 🧠 2 2 + Reply
Running on Zero MCP 265 Qwen Image 2.1 Uncensored All-In-One LoRA Studio 🚀 265 Uncensored Qwen 2.1 with All-In-One LoRAs
Running on Zero MCP 411 Qwen Image 2.1 Uncensored GGUF Studio 🎨 411 Qwen-Image-2.1 Uncensored GGUF demo on ZeroGPU
Running EmbeddingGemma 2 — five experiments ✨ 3D meaning map, photo search, voice remote, word game, axes
Running EmbeddingGemma 2 — five experiments ✨ 3D meaning map, photo search, voice remote, word game, axes
Running on Zero Agents 101 Voice Cloning Studio 🚀 101 This space offers an easy-to-use interface for voice cloning