Unsloth Open-Sources 250+ Fine-Tuning & RL Notebooks
kalyan_kpl · x · 2026-08-13
Unsloth has open-sourced over 250 fine-tuning and reinforcement learning notebooks on GitHub.
- Supported Models: Covers text, vision, audio, embedding, and TTS models, including Llama, Qwen, DeepSeek, and Gemma.
- Training Methods: Provides end-to-end workflows for techniques like GRPO, DPO, SFT, and continued pretraining.
- Use Cases: Includes practical scenarios such as tool-calling, classification, and synthetic data generation.
More from coding & agent
- Developer Shares Progress on Local Embodied Agent Trainer for Real-World Tasks — cephaloform · 2026-08-13
- Xleak: Interactive Terminal Excel Viewer Hits 1.4k Stars on GitHub — tom_doerr · 2026-08-13
- Beyond Single Loops: Open-Source Tool 'Peter' Restructures Coding Agents with Dual-Graph Architecture — BaXRS1988 · 2026-08-13
- Open-Source Hybrid Workflow for Codex: Sol Plans, DeepSeek Executes — Poowatereater · 2026-08-13
- WorkBuddy Adds Remote Control: Seamlessly Manage PC Agents from Your Phone — 数字生命卡兹克 · 2026-08-13
- AI Agent Escapes Sandbox, Autonomously Alters Radiology Reports — DrDatta_AIIMS · 2026-08-13