Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
fix(template): remove duplicate frontmatter block from bug issue template (#10392)
陈志谦0b2b0b2a99b4
diff --git a/.github/ISSUE_TEMPLATE/bug---issue.md b/.github/ISSUE_TEMPLATE/bug---issue.mdindex de1280b3788..6a7e722e2af 100644--- a/.github/ISSUE_TEMPLATE/bug---issue.md+++ b/.github/ISSUE_TEMPLATE/bug---issue.md@@ -7,14 +7,6 @@ assignees: ''--------name: Unsloth Studio Bug-about: Report a problem with the Unsloth Studio desktop app or web UI-title: "[Unsloth Bug] "-labels: bug-assignees: ""-----<!--Search existing issues before submitting. Please do not remove the questions.Never post API keys, Hugging Face tokens, passwords, cookies, private prompts,diff --git a/README.md b/README.mdindex 22942cf4ef4..de20157ba19 100644--- a/README.md+++ b/README.md@@ -88,7 +88,7 @@ Unsloth works on **Windows, Linux, WSL** and **macOS**. We support **Multi GPU s### Train & Deploy* **Fine-tuning:** Train LLMs, diffusion, TTS, and embedding models 2× faster with 70% less VRAM with [no accuracy loss](https://unsloth.ai/blog#training)* **Complete support:** Supports [reinforcement learning](https://unsloth.ai/docs/get-started/reinforcement-learning-rl-guide), LoRA, QLoRA, full fine tuning, pretraining, RL, GRPO, DPO, and FP8.-* **Export & Deploy:** [Export](https://unsloth.ai/docs/new/studio/export) or Deploy models with including [GGUF](https://unsloth.ai/docs/basics/inference-and-deployment/saving-to-gguf), NVFP4, FP8 and more formats.+* **Export & Deploy:** [Export](https://unsloth.ai/docs/new/studio/export) or Deploy models including [GGUF](https://unsloth.ai/docs/basics/inference-and-deployment/saving-to-gguf), NVFP4, FP8 and more formats.* **Datasets:** Build datasets from PDFs, CSVs, DOCX files, and more with [Data Recipes](https://unsloth.ai/docs/new/studio/data-recipe).## 🚀 Unsloth Startdiff --git a/unsloth/save.py b/unsloth/save.pyindex d24e9452acb..4d7e119f16c 100644--- a/unsloth/save.py+++ b/unsloth/save.py@@ -1002,7 +1002,7 @@ def unsloth_save_model(if save_method != "lora" and save_method != "merged_16bit" and save_method != "merged_4bit":raise RuntimeError("Unsloth: You must select one of 3 options when saving models:\n"- '"lora" ==> This is the fastest and easiet. Just saves LoRA modules.\n'+ '"lora" ==> This is the fastest and easiest. Just saves LoRA modules.\n''"merged_16bit" ==> This merges LoRA weights and saves to float16. Needed for llama.cpp / GGUF.\n''"merged_4bit" ==> This merges LoRA weights and saves to 4bit. Useful for DPO / inference.')