Feat: add ministral3 (#3297)

* feat: add ministral and mistral3

* chore: lint

* feat: update cce for ministral

* fix: add vram usage

* feat: update for release

* fix: save_pretrained issue in v5

* fix: add instructions to use v5 branch

* fix: add to multipack

* fix: improve instructions

* fix: add model to readme

src/axolotl/integrations/cut_cross_entropy/README.md

@@ -19,7 +19,7 @@ python scripts/cutcrossentropy_install.py | sh
 
 - If you are installing from pip
 ```bash
-pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@5eff953"
+pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@f643b88"
 ```
 
 ## Usage
@@ -61,6 +61,8 @@ plugins:
 - llama4
 - llama4_text
 - llava
+- ministral
+- ministral3
 - mistral
 - mistral3
 - mixtral

src/axolotl/integrations/cut_cross_entropy/__init__.py

@@ -35,7 +35,7 @@ LOG = get_logger(__name__)
 
 _CCE_INSTALL_MESSAGE = (
     "Please install Axolotl's fork of cut_cross_entropy with transformers support using "
-    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@5eff953"`'
+    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@f643b88"`'
 )
 
 

src/axolotl/monkeypatch/multipack.py

@@ -52,6 +52,8 @@ SUPPORTED_MULTIPACK_MODEL_TYPES = [
     "olmo",
     "olmo2",
     "olmo3",
+    "ministral",
+    "ministral3",
     "afmoe",
 ]
 

src/axolotl/utils/mistral/mistral_tokenizer.py

@@ -218,3 +218,10 @@ class HFMistralTokenizer(MistralCommonTokenizer):
             model_input_names=model_input_names,
             clean_up_tokenization_spaces=clean_up_tokenization_spaces,
         )
+
+    def save_pretrained(self, *args, **kwargs) -> tuple[str, ...]:
+        """
+        Patches to remove save_jinja_files from being passed onwards.
+        """
+        kwargs.pop("save_jinja_files", None)
+        return super().save_pretrained(*args, **kwargs)