diff --git a/.github/ISSUE_TEMPLATE/bug---issue.md b/.github/ISSUE_TEMPLATE/bug---issue.md new file mode 100644 index 0000000000..a08a6cf2cf --- /dev/null +++ b/.github/ISSUE_TEMPLATE/bug---issue.md @@ -0,0 +1,19 @@ +--- +name: Bug / Issue +about: Bug / Issue +title: "[Bug]" +labels: bug +assignees: '' + +--- + +1. Did you update? `pip install --upgrade unsloth unsloth_zoo` +2. `Colab` or `Kaggle` or local / cloud +3. Number GPUs used, use `nvidia-smi` +4. Which notebook? +5. Paste `Unsloth` printout with :sloth: sloth emoji +6. Which trainer? `SFTTrainer`, `GRPOTrainer` etc +7. **Minimal code to reproduce error Remove Hugging Face token!** + +For quick replies, got to https://discord.com/invite/unsloth. +Have you tried https://docs.unsloth.ai/basics/errors-troubleshooting diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md deleted file mode 100644 index 4c6ab77d83..0000000000 --- a/.github/ISSUE_TEMPLATE/bug_report.md +++ /dev/null @@ -1,41 +0,0 @@ ---- -name: 🐛 Bug report -about: Create a report to help us improve -title: "[Bug]" -labels: bug -assignees: '' - ---- - -**Describe the bug** -A clear and concise description of what the bug is. Please fill out the following sections and provide a minimal reproduction script so that we can provide a solution as quickly as possible! - -1. **Environment Setup:** - - OS: [e.g., Ubuntu 20.04] - - Python Version: [e.g., 3.8.10] - - Frameworks/Libraries: please paste output of `pip freeze` here - - `colab` / script - was this run in `colab` or as a script? - -2. **Dataset Details:** - - Dataset Name: - - Data Preprocessing Steps: [e.g., tokenization, formatting funcs, data collators, etc.] - -3. **Model Details:** - - Model ID: - - Model Configuration: [e.g., lora params, quantization, etc.] - -4. **Training Configuration:** - - Trainer Args: `SFTConfig`, `GRPOConfig` - -5. **Reproduction Steps:** - - Minimal script to reproduce error - - If using a `colab`, please provide the link to the notebook and describe any changes made. - -6. **Expected Behavior:** - -7. **Actual Behavior:** - - [e.g., Description of the error, unexpected results, or performance issues encountered] - - [e.g., Error messages or logs] - -8. **Additional notes:** - - Any additional information that might help us reproduce the bug. diff --git a/.github/ISSUE_TEMPLATE/documentation.md b/.github/ISSUE_TEMPLATE/documentation.md deleted file mode 100644 index 19af72486e..0000000000 --- a/.github/ISSUE_TEMPLATE/documentation.md +++ /dev/null @@ -1,34 +0,0 @@ ---- -name: 📚 Documentation -about: Report incorrect or needed docs for https://docs.unsloth.ai/ -title: "[Docs]" -labels: documentation -assignees: '' - ---- - -- [ ] Report incorrect documentation -- [ ] Report needed documentation - -## Report incorrect documentation - -**Location of incorrect documentation -- provide links and line numbers if possible.** - -**Describe the problems or issues found in the documentation** - -**Steps taken to verify documentation is incorrect** - -**Suggested fix** - ---- - -## Report needed documentation - -**What's missing?** - - -**Describe the documentation you'd like -- how can we make using `unsloth` easier?** - - -**Help us understand how we can make finding the needed info easier!** -List any steps you have taken, e.g. searching the repo, reading the docs, etc. diff --git a/.github/ISSUE_TEMPLATE/feature-request.md b/.github/ISSUE_TEMPLATE/feature-request.md new file mode 100644 index 0000000000..5ea70a8a03 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/feature-request.md @@ -0,0 +1,21 @@ +--- +name: Feature Request +about: New features, model support, ideas +title: "[Feature]" +labels: feature request +assignees: '' + +--- + +For new models, have you tried: +```python +from unsloth import FastModel +model, tokenizer = FastModel.from_pretrained( + "microsoft/Phi-4-multimodal-instruct", + trust_remote_code = True, +) +from transformers import AutoModelForSequenceClassification +model, tokenizer = FastModel.from_pretrained( + auto_model = AutoModelForSequenceClassification, +) +``` diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md deleted file mode 100644 index 7f7d93c0f6..0000000000 --- a/.github/ISSUE_TEMPLATE/feature_request.md +++ /dev/null @@ -1,14 +0,0 @@ ---- -name: 🚀 Feature request -about: "Suggest an idea: new model, algorithm or feature etc." -title: "[Feature]" -labels: "feature request" -assignees: '' - ---- - -**What features would you like to see? Is it related to a problem or a new feature you'd like to see? Please describe.** -What we can do to improve `unsloth`? - -**Additional context** -Feel free to add any other context, links, or screenshots here. diff --git a/.github/ISSUE_TEMPLATE/question.md b/.github/ISSUE_TEMPLATE/question.md deleted file mode 100644 index 90aa1284d7..0000000000 --- a/.github/ISSUE_TEMPLATE/question.md +++ /dev/null @@ -1,10 +0,0 @@ ---- -name: ❓ Submit question -about: Ask a general question about unsloth -title: "[Question]" -labels: "question" -assignees: '' - ---- - -**What is your question?** diff --git a/README.md b/README.md index 74c5e8afac..95492b6ef3 100644 --- a/README.md +++ b/README.md @@ -30,7 +30,7 @@ Notebooks are beginner friendly. Read our [guide](https://docs.unsloth.ai/get-st | **Llama 3.2 Vision (11B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x faster | 50% less | | **Llama 3.1 (8B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb) | 2x faster | 70% less | | **Mistral v0.3 (7B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Mistral_v0.3_(7B)-Conversational.ipynb) | 2.2x faster | 75% less | -| **Sesame-CSM (1B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Orpheus_(3B)-TTS.ipynb) | 1.5x faster | 50% less | +| **Sesame-CSM (1B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Sesame_CSM_(1B)-TTS.ipynb) | 1.5x faster | 50% less | - See all our notebooks for: [Kaggle](https://github.com/unslothai/notebooks?tab=readme-ov-file#-kaggle-notebooks), [GRPO](https://docs.unsloth.ai/get-started/unsloth-notebooks#grpo-reasoning-notebooks), **[TTS](https://docs.unsloth.ai/get-started/unsloth-notebooks#text-to-speech-tts-notebooks)** & [Vision](https://docs.unsloth.ai/get-started/unsloth-notebooks#vision-multimodal-notebooks) - See [all our models](https://docs.unsloth.ai/get-started/all-our-models) and our [Synthetic Dataset notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Meta_Synthetic_Data_Llama3_2_%283B%29.ipynb) in collaboration with Meta @@ -77,6 +77,7 @@ For Windows install instructions, see [here](https://docs.unsloth.ai/get-started ## ⭐ Key Features - Supports **full-finetuning**, pretraining, 4b-bit, 16-bit and **8-bit** training +- Supports **all transformer-style models** including [TTS, STT](https://docs.unsloth.ai/basics/text-to-speech-tts-fine-tuning), multimodal, diffusion, [BERT](https://docs.unsloth.ai/get-started/unsloth-notebooks#other-important-notebooks) and more! - All kernels written in [OpenAI's Triton](https://openai.com/index/triton/) language. **Manual backprop engine**. - **0% loss in accuracy** - no approximation methods - all exact. - No change of hardware. Supports NVIDIA GPUs since 2018+. Minimum CUDA Capability 7.0 (V100, T4, Titan V, RTX 20, 30, 40x, A100, H100, L40 etc) [Check your GPU!](https://developer.nvidia.com/cuda-gpus) GTX 1070, 1080 works, but is slow. diff --git a/pyproject.toml b/pyproject.toml index 558abd9f1a..7fb572b735 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -37,7 +37,7 @@ triton = [ ] huggingface = [ - "unsloth_zoo>=2025.5.7", + "unsloth_zoo>=2025.5.8", "packaging", "tyro", "transformers==4.51.3,!=4.47.0", @@ -381,7 +381,7 @@ colab-ampere-torch220 = [ "flash-attn>=2.6.3", ] colab-new = [ - "unsloth_zoo>=2025.5.7", + "unsloth_zoo>=2025.5.8", "packaging", "tyro", "transformers==4.51.3,!=4.47.0", diff --git a/unsloth/models/_utils.py b/unsloth/models/_utils.py index 747858d011..964e874c58 100644 --- a/unsloth/models/_utils.py +++ b/unsloth/models/_utils.py @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. -__version__ = "2025.5.6" +__version__ = "2025.5.7" __all__ = [ "SUPPORTS_BFLOAT16", diff --git a/unsloth/models/mapper.py b/unsloth/models/mapper.py index e50a5a877d..50f0f7d7fb 100644 --- a/unsloth/models/mapper.py +++ b/unsloth/models/mapper.py @@ -849,6 +849,21 @@ __INT_TO_FLOAT_MAPPER = \ "unsloth/Llama-OuteTTS-1.0-1B", "OuteAI/Llama-OuteTTS-1.0-1B", ), + "unsloth/medgemma-4b-it-unsloth-bnb-4bit" : ( + "unsloth/medgemma-4b-it", + "google/medgemma-4b-it", + "unsloth/medgemma-4b-it-bnb-4bit", + ), + "unsloth/medgemma-27b-text-it-unsloth-bnb-4bit" : ( + "unsloth/medgemma-27b-text-it", + "google/medgemma-27b-text-it", + "unsloth/medgemma-27b-text-it-bnb-4bit", + ), + "unsloth/Devstral-Small-2505-unsloth-bnb-4bit" : ( + "unsloth/Devstral-Small-2505", + "mistralai/Devstral-Small-2505", + "unsloth/Devstral-Small-2505-bnb-4bit", + ), } INT_TO_FLOAT_MAPPER = {}