feat: add apertus model and cce (#3144) [skip ci]

* feat: add apertus, glm4v, glm4v_moe cce

* fix: arcee docs

* feat: add apertus

* feat: added vram usage

* fix: add apertus note

* feat: update doc on apertus xielu

* fix: add monkeypatch for xielu activation issue

* fix: simplify env

* feat: pin commit

* feat: add packing

* chore: move patch calling

* Update examples/apertus/README.md

Co-authored-by: salman <salman.mohammadi@outlook.com>

* Update examples/apertus/README.md

Co-authored-by: salman <salman.mohammadi@outlook.com>

* Update examples/apertus/README.md

Co-authored-by: salman <salman.mohammadi@outlook.com>

---------

Co-authored-by: salman <salman.mohammadi@outlook.com>

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@c6a32c5"
+pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@c564afc"
 ```
 
 ## Usage

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@c6a32c5"`'
+    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@c564afc"`'
 )
 
 

src/axolotl/loaders/patch_manager.py

@@ -68,11 +68,12 @@ class PatchManager:
         self._apply_self_attention_lora_patch()
         self._apply_fsdp2_bnb_patches()
         self._apply_patch_deepspeed_zero3()
+        self._apply_voxtral_patches()
+        self._apply_apertus_patches()
 
     def apply_post_plugin_pre_model_load_patches(self):
         """Apply post plugin-pre_model_load load patches based on config."""
         self._apply_tiled_mlp(self.cfg.model_config_type)
-        self._apply_voxtral_patches()
 
     def _apply_transformers_patches(self):
         from axolotl.monkeypatch.transformers.trainer_loss_calc import (
@@ -493,3 +494,12 @@ class PatchManager:
                 apply_deepspeed_patches()
         except ImportError as e:
             LOG.warning(f"DeepSpeed patches not applied: {e}")
+
+    def _apply_apertus_patches(self):
+        """Apply patches for Apertus model."""
+        if self.cfg.model_config_type == "apertus":
+            from axolotl.monkeypatch.models.apertus.activation import (
+                patch_apertus_xielu_activation,
+            )
+
+            patch_apertus_xielu_activation()

src/axolotl/monkeypatch/models/apertus/activation.py

@@ -0,0 +1,52 @@
+"""Monkeypatch for Apertus to dtype mismatch in XIELU act"""
+
+from torch import Tensor
+
+
+def patch_apertus_xielu_activation():
+    try:
+        from transformers.activations import XIELUActivation
+    except ImportError as err:
+        raise ImportError(
+            "Cannot import XIELUActivation. "
+            "Please make sure to update your transformers version >= 4.56.1."
+        ) from err
+
+    from transformers.activations import logger
+
+    # Store the original method
+    old_fn = XIELUActivation._xielu_cuda
+
+    def _xielu_cuda_fixed(self, x: Tensor) -> Tensor:
+        """Firewall function to prevent torch.compile from seeing .item() calls"""
+        original_shape = x.shape
+        # CUDA kernel expects 3D tensors, reshape if needed
+        while x.dim() < 3:
+            x = x.unsqueeze(0)
+        if x.dim() > 3:
+            x = x.view(-1, 1, x.size(-1))
+        if original_shape != x.shape:
+            logger.warning_once(
+                "Warning: xIELU input tensor expects 3 dimensions but got (shape: %s). Reshaping to (shape: %s).",
+                original_shape,
+                x.shape,
+            )
+        result = self._xielu_cuda_obj.forward(
+            x,
+            self.alpha_p.to(x.dtype),
+            self.alpha_n.to(x.dtype),
+            # Temporary until xIELU CUDA fully implemented -> self.{beta,eps}.item()
+            self._beta_scalar,
+            self._eps_scalar,
+            self.with_vector_loads,
+        )
+        return result.view(original_shape)
+
+    # Apply the patch
+    XIELUActivation._xielu_cuda = _xielu_cuda_fixed
+
+    def unpatch():
+        """Restore the original method"""
+        XIELUActivation._xielu_cuda = old_fn
+
+    return unpatch

src/axolotl/monkeypatch/multipack.py

@@ -11,6 +11,7 @@ from axolotl.monkeypatch.mixtral import patch_mixtral_moe_forward_zero3
 from axolotl.monkeypatch.utils import get_unpad_data
 
 SUPPORTED_MULTIPACK_MODEL_TYPES = [
+    "apertus",
     "mllama_text_model",
     "llama",
     "llama4",