adding fp32 support

* feat: upgrade cce with patches for transformers 4.56

* feat: add missing models to cce readme

examples/colab-notebooks/colab-axolotl-example.ipynb

@@ -40,7 +40,7 @@
     "%%capture\n",
     "# This step can take ~5-10 minutes to install dependencies\n",
     "!pip install --no-build-isolation axolotl[flash-attn]>=0.9.1\n",
-    "!pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@c5aa3ef\""
+    "!pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@147ea28\""
    ]
   },
   {

scripts/cutcrossentropy_install.py

@@ -29,5 +29,5 @@ UV_PREFIX = "uv " if USE_UV else ""
 
 print(
     UNINSTALL_PREFIX
-    + f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@c5aa3ef"'
+    + f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@147ea28"'
 )

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@c5aa3ef"
+pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@147ea28"
 ```
 
 ## Usage
@@ -31,6 +31,7 @@ plugins:
 
 ## Supported Models
 
+- apertus
 - arcee
 - cohere
 - cohere2
@@ -44,9 +45,13 @@ plugins:
 - glm
 - glm4
 - glm4_moe
+- glm4v
+- glm4v_moe
 - gpt_oss
 - granite
 - granitemoe
+- granitemoeshared
+- granitemoehybrid
 - hunyuan_v1_dense
 - hunyuan_v1_moe
 - llama
@@ -65,6 +70,8 @@ plugins:
 - qwen2_5_vl
 - qwen3
 - qwen3_moe
+- qwen3_vl
+- qwen3_vl_moe
 - qwen3_next
 - smollm3
 - seed_oss

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@c5aa3ef"`'
+    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@147ea28"`'
 )
 
 

src/axolotl/monkeypatch/accelerate/fsdp2.py

@@ -368,6 +368,7 @@ def fsdp2_prepare_model(accelerator, model: torch.nn.Module) -> torch.nn.Module:
         # removing the call above leads to extra memory usage as explained in the comment above
         if hasattr(model, "tie_weights"):
             model.tie_weights()
+    model = model.to(torch.float32)
     return model