From af51e7df8752cda7fbad5f4f2bb2baff7c1b4637 Mon Sep 17 00:00:00 2001 From: zhaozh Date: Wed, 2 Apr 2025 16:10:21 +0800 Subject: [PATCH 01/10] Update README.md Gemma3 HF uploaded GGUFs, 4-bit models link. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 423689bb54..696bf2aca5 100644 --- a/README.md +++ b/README.md @@ -48,7 +48,7 @@ For Windows install instructions, see [here](https://docs.unsloth.ai/get-started ## 🦥 Unsloth.ai News - 📣 NEW! [**EVERYTHING** is now supported](https://unsloth.ai/blog/gemma3#everything) incuding: FFT, ALL models (Mixtral, MOE, Cohere, Mamba) and all training algorithms (KTO, DoRA) etc. MultiGPU support coming very soon. To enable full-finetuning, set ```full_finetuning = True``` and for 8-bit finetuning, set ```load_in_8bit = True``` -- 📣 NEW! **Gemma 3** by Google: [Read Blog](https://unsloth.ai/blog/gemma3). We [uploaded GGUFs, 4-bit models](https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa). +- 📣 NEW! **Gemma 3** by Google: [Read Blog](https://unsloth.ai/blog/gemma3). We [uploaded GGUFs, 4-bit models](https://huggingface.co/collections/unsloth/gemma-3-67d12b7e8816ec6efa7e4e5b). - 📣 NEW! Introducing Long-context [Reasoning (GRPO)](https://unsloth.ai/blog/grpo) in Unsloth. Train your own reasoning model with just 5GB VRAM. Transform Llama, Phi, Mistral etc. into reasoning LLMs! - 📣 NEW! [DeepSeek-R1](https://unsloth.ai/blog/deepseek-r1) - the most powerful open reasoning models with Llama & Qwen distillations. Run or fine-tune them now [with our guide](https://unsloth.ai/blog/deepseek-r1). All model uploads: [here](https://huggingface.co/collections/unsloth/deepseek-r1-all-versions-678e1c48f5d2fce87892ace5). - 📣 NEW! [Phi-4](https://unsloth.ai/blog/phi4) by Microsoft: We also [fixed bugs](https://unsloth.ai/blog/phi4) in Phi-4 and [uploaded GGUFs, 4-bit](https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa). From 3cee1031384c13071e68bbcd0a0a8e09938336b3 Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Sat, 5 Apr 2025 14:56:01 -0700 Subject: [PATCH 02/10] Update README.md --- README.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 696bf2aca5..2353708297 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ -### Finetune Llama 3.3, Gemma 3, Phi-4, Qwen 2.5 & Mistral 2x faster with 80% less VRAM! +### Finetune Llama 4, Gemma 3, Phi-4, Qwen 2.5 & Mistral 2x faster with 80% less VRAM! ![](https://i.ibb.co/sJ7RhGG/image-41.png) @@ -46,19 +46,20 @@ pip install unsloth For Windows install instructions, see [here](https://docs.unsloth.ai/get-started/installing-+-updating/windows-installation). ## 🦥 Unsloth.ai News +- 📣 NEW! **[Llama 4](https://unsloth.ai/blog/llama4)**, Meta's latest models including Scout & Maverick are now supported. - 📣 NEW! [**EVERYTHING** is now supported](https://unsloth.ai/blog/gemma3#everything) incuding: FFT, ALL models (Mixtral, MOE, Cohere, Mamba) and all training algorithms (KTO, DoRA) etc. MultiGPU support coming very soon. To enable full-finetuning, set ```full_finetuning = True``` and for 8-bit finetuning, set ```load_in_8bit = True``` - 📣 NEW! **Gemma 3** by Google: [Read Blog](https://unsloth.ai/blog/gemma3). We [uploaded GGUFs, 4-bit models](https://huggingface.co/collections/unsloth/gemma-3-67d12b7e8816ec6efa7e4e5b). - 📣 NEW! Introducing Long-context [Reasoning (GRPO)](https://unsloth.ai/blog/grpo) in Unsloth. Train your own reasoning model with just 5GB VRAM. Transform Llama, Phi, Mistral etc. into reasoning LLMs! - 📣 NEW! [DeepSeek-R1](https://unsloth.ai/blog/deepseek-r1) - the most powerful open reasoning models with Llama & Qwen distillations. Run or fine-tune them now [with our guide](https://unsloth.ai/blog/deepseek-r1). All model uploads: [here](https://huggingface.co/collections/unsloth/deepseek-r1-all-versions-678e1c48f5d2fce87892ace5). - 📣 NEW! [Phi-4](https://unsloth.ai/blog/phi4) by Microsoft: We also [fixed bugs](https://unsloth.ai/blog/phi4) in Phi-4 and [uploaded GGUFs, 4-bit](https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa). -- 📣 NEW! [Llama 3.3 (70B)](https://huggingface.co/collections/unsloth/llama-33-all-versions-67535d7d994794b9d7cf5e9f), Meta's latest model is supported. - 📣 Introducing Unsloth [Dynamic 4-bit Quantization](https://unsloth.ai/blog/dynamic-4bit)! We dynamically opt not to quantize certain parameters and this greatly increases accuracy while only using <10% more VRAM than BnB 4-bit. See our collection on [Hugging Face here.](https://huggingface.co/collections/unsloth/unsloth-4-bit-dynamic-quants-67503bb873f89e15276c44e7) - 📣 [Vision models](https://unsloth.ai/blog/vision) now supported! [Llama 3.2 Vision (11B)](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb), [Qwen 2.5 VL (7B)](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2_VL_(7B)-Vision.ipynb) and [Pixtral (12B) 2409](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Pixtral_(12B)-Vision.ipynb)
Click for more news -- 📣 NEW! We worked with Apple to add [Cut Cross Entropy](https://arxiv.org/abs/2411.09009). Unsloth now supports 89K context for Meta's Llama 3.3 (70B) on a 80GB GPU - 13x longer than HF+FA2. For Llama 3.1 (8B), Unsloth enables 342K context, surpassing its native 128K support. +- 📣 [Llama 3.3 (70B)](https://huggingface.co/collections/unsloth/llama-33-all-versions-67535d7d994794b9d7cf5e9f), Meta's latest model is supported. +- 📣 We worked with Apple to add [Cut Cross Entropy](https://arxiv.org/abs/2411.09009). Unsloth now supports 89K context for Meta's Llama 3.3 (70B) on a 80GB GPU - 13x longer than HF+FA2. For Llama 3.1 (8B), Unsloth enables 342K context, surpassing its native 128K support. - 📣 We found and helped fix a [gradient accumulation bug](https://unsloth.ai/blog/gradient)! Please update Unsloth and transformers. - 📣 Try out [Chat interface](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Unsloth_Studio.ipynb)! - 📣 NEW! Qwen-2.5 including [Coder](https://unsloth.ai/blog/qwen-coder) models are now supported with bugfixes. 14b fits in a Colab GPU! [Qwen 2.5 conversational notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_Coder_(14B)-Conversational.ipynb) From 823396d3f0ecd653c0444ba4623bcf1fe2319c22 Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:17:33 -0700 Subject: [PATCH 03/10] Update bug_report.md --- .github/ISSUE_TEMPLATE/bug_report.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md index cf4f07a9bf..1d9e2f92f6 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.md +++ b/.github/ISSUE_TEMPLATE/bug_report.md @@ -1,7 +1,7 @@ --- name: Bug report about: Create a report to help us improve -title: "[BUG]" +title: "[Bug]" labels: bug assignees: '' @@ -38,4 +38,4 @@ A clear and concise description of what the bug is. Please fill out the followi - [e.g., Error messages or logs] 8. **Additional notes:** - - Any additional information that might help us reproduce the bug. \ No newline at end of file + - Any additional information that might help us reproduce the bug. From dcbc4893183520d5b21d66dc87433d2966ec795e Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:19:40 -0700 Subject: [PATCH 04/10] Update documentation.md --- .github/ISSUE_TEMPLATE/documentation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/ISSUE_TEMPLATE/documentation.md b/.github/ISSUE_TEMPLATE/documentation.md index b8833510f4..e7bc749196 100644 --- a/.github/ISSUE_TEMPLATE/documentation.md +++ b/.github/ISSUE_TEMPLATE/documentation.md @@ -1,7 +1,7 @@ --- name: Documentation about: Report incorrect or needed documentation to improve unsloth! -title: "[DOC]" +title: "[Docs]" labels: documentation assignees: '' From 939fe82763dda2720c8a09acb4fe6e02b6fdc019 Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:20:06 -0700 Subject: [PATCH 05/10] Update feature_request.md --- .github/ISSUE_TEMPLATE/feature_request.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md index f6f78c0841..6fbdfcf0e6 100644 --- a/.github/ISSUE_TEMPLATE/feature_request.md +++ b/.github/ISSUE_TEMPLATE/feature_request.md @@ -1,7 +1,7 @@ --- name: Feature request about: "Suggest an idea: new algorithm, model, kernel, etc." -title: "[FEAT]" +title: "[Feature]" labels: "feature request" assignees: '' From a40a4e0e7d425aa271a8486a1369742572cd4f85 Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:20:44 -0700 Subject: [PATCH 06/10] Update question.md --- .github/ISSUE_TEMPLATE/question.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/ISSUE_TEMPLATE/question.md b/.github/ISSUE_TEMPLATE/question.md index 0df891dacf..8f99361329 100644 --- a/.github/ISSUE_TEMPLATE/question.md +++ b/.github/ISSUE_TEMPLATE/question.md @@ -1,7 +1,7 @@ --- name: Submit question about: Ask a general question about unsloth -title: "[QST]" +title: "[Question]" labels: "question" assignees: '' From fee6e6ed4d3242a1d15c0ab64785fb55f4a8d38d Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:24:35 -0700 Subject: [PATCH 07/10] Update bug_report.md --- .github/ISSUE_TEMPLATE/bug_report.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md index 1d9e2f92f6..4c6ab77d83 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.md +++ b/.github/ISSUE_TEMPLATE/bug_report.md @@ -1,5 +1,5 @@ --- -name: Bug report +name: 🐛 Bug report about: Create a report to help us improve title: "[Bug]" labels: bug From 67f7aae50520412df8ee129a8acaf01f14af1202 Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:29:20 -0700 Subject: [PATCH 08/10] Update documentation.md --- .github/ISSUE_TEMPLATE/documentation.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/documentation.md b/.github/ISSUE_TEMPLATE/documentation.md index e7bc749196..19af72486e 100644 --- a/.github/ISSUE_TEMPLATE/documentation.md +++ b/.github/ISSUE_TEMPLATE/documentation.md @@ -1,6 +1,6 @@ --- -name: Documentation -about: Report incorrect or needed documentation to improve unsloth! +name: 📚 Documentation +about: Report incorrect or needed docs for https://docs.unsloth.ai/ title: "[Docs]" labels: documentation assignees: '' From 9e57990b7f031e2bcfb1e9e71157fc18a6a5c927 Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:30:56 -0700 Subject: [PATCH 09/10] Update feature_request.md --- .github/ISSUE_TEMPLATE/feature_request.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md index 6fbdfcf0e6..7f7d93c0f6 100644 --- a/.github/ISSUE_TEMPLATE/feature_request.md +++ b/.github/ISSUE_TEMPLATE/feature_request.md @@ -1,6 +1,6 @@ --- -name: Feature request -about: "Suggest an idea: new algorithm, model, kernel, etc." +name: 🚀 Feature request +about: "Suggest an idea: new model, algorithm or feature etc." title: "[Feature]" labels: "feature request" assignees: '' From c37c0ed5c2a5dda4daa33b554686a11800e9045e Mon Sep 17 00:00:00 2001 From: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Date: Wed, 9 Apr 2025 15:31:56 -0700 Subject: [PATCH 10/10] Update question.md --- .github/ISSUE_TEMPLATE/question.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/ISSUE_TEMPLATE/question.md b/.github/ISSUE_TEMPLATE/question.md index 8f99361329..90aa1284d7 100644 --- a/.github/ISSUE_TEMPLATE/question.md +++ b/.github/ISSUE_TEMPLATE/question.md @@ -1,5 +1,5 @@ --- -name: Submit question +name: ❓ Submit question about: Ask a general question about unsloth title: "[Question]" labels: "question"