From 8febcdf6e0c751265d11229980002d53e919583d Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Thu, 10 Jul 2025 07:03:48 -0700 Subject: [PATCH] Many bug fixes (#2927) * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py --------- Co-authored-by: jeromeku Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> --- pyproject.toml | 4 ++-- unsloth/__init__.py | 2 +- unsloth/models/_utils.py | 2 +- unsloth/models/llama.py | 2 +- unsloth/models/mapper.py | 5 +++++ 5 files changed, 10 insertions(+), 5 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 8b24a52a6f..b538578fd5 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -37,7 +37,7 @@ triton = [ ] huggingface = [ - "unsloth_zoo>=2025.7.1", + "unsloth_zoo>=2025.7.2", "packaging", "tyro", "transformers>=4.51.3,!=4.47.0,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3", @@ -381,7 +381,7 @@ colab-ampere-torch220 = [ "flash-attn>=2.6.3", ] colab-new = [ - "unsloth_zoo>=2025.7.1", + "unsloth_zoo>=2025.7.2", "packaging", "tyro", "transformers>=4.51.3,!=4.47.0,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3", diff --git a/unsloth/__init__.py b/unsloth/__init__.py index 4da08da13d..e965b2959e 100644 --- a/unsloth/__init__.py +++ b/unsloth/__init__.py @@ -79,7 +79,7 @@ def get_device_count(): elif DEVICE_TYPE == "xpu": return torch.xpu.device_count() else: - return 0 + return 1 pass DEVICE_COUNT : int = get_device_count() diff --git a/unsloth/models/_utils.py b/unsloth/models/_utils.py index c6ff7b6260..5076c422c8 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__ = "2025.7.1" +__version__ = "2025.7.2" __all__ = [ "SUPPORTS_BFLOAT16", diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index db0e8843cf..8ccdeba353 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -796,7 +796,7 @@ def LlamaModel_fast_forward( # Ignore attention_mask if attention_mask is None: padding_mask = None - elif self.training and os.environ.get("UNSLOTH_KEEP_PADDING", "0") != '1': + elif self.training: attention_mask = None padding_mask = None else: diff --git a/unsloth/models/mapper.py b/unsloth/models/mapper.py index 62259841c5..f559c6c01e 100644 --- a/unsloth/models/mapper.py +++ b/unsloth/models/mapper.py @@ -899,6 +899,11 @@ __INT_TO_FLOAT_MAPPER = \ "google/gemma-3n-E2B", "unsloth/gemma-3n-E2B-unsloth-bnb-4bit", ), + "unsloth/Devstral-Small-2507-unsloth-bnb-4bit" : ( + "unsloth/Devstral-Small-2507", + "mistralai/Devstral-Small-2507", + "unsloth/Devstral-Small-2507-bnb-4bit", + ), } INT_TO_FLOAT_MAPPER = {}