Fine-tune Google's Gemma 3(unsloth.ai)
208 points by tomdekan | 68 comments
First screen, captured .
Looks similar
Run DeepSeek R1 Dynamic 1.58-bit(unsloth.ai)
701 points by noch | 308 comments
Unsloth blog post describing dynamic 1.58-bit quantization of DeepSeek-R1 671B, shrinking it to 131GB so users can run it locally.
Long-Context GRPO(unsloth.ai)
48 points by veryluckyxyz | 15 comments
Unsloth Studio(unsloth.ai)
364 points by brainless | 67 comments
Announcement page for Unsloth Studio (Beta), an open-source no-code web UI for training, running, and exporting open AI models locally.
Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B(phind.com)
737 points by rushingcreek | 258 comments
Phind blog post announcing fine-tuned CodeLlama-34B models that score 67.6% and 69.5% pass@1 on HumanEval, beating GPT-4's reported 67%.
Qwen3.5 Fine-Tuning Guide(unsloth.ai)
384 points by bilsbie | 93 comments
Unsloth documentation guide explaining how to fine-tune Qwen3.5 LLMs (0.8B to 122B) with LoRA, including VRAM requirements and free Colab notebooks.