License->MIT; strip training-only code (init_weights, torch._dynamo config, stochastic depth). Inference forward bit-identical (verified).

LICENSE

@@ -1,202 +1,21 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
+MIT License
+
+Copyright (c) 2026 Motif Technologies
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: mit
 library_name: transformers
 pipeline_tag: image-feature-extraction
 tags:
@@ -109,7 +109,7 @@ video. Comparison numbers are the best figures reported by each model's authors.
 
 ## License
 
-Released under **Apache-2.0** (see `LICENSE`). The model was trained on data governed by the
+Released under the **MIT License** (see `LICENSE`). The model was trained on data governed by the
 respective dataset licenses; downstream users are responsible for compliance with those terms.
 
 ## Citation

modeling_motif.py

@@ -47,30 +47,6 @@ def uncat_with_shapes(flattened: Tensor, shapes: list[tuple[int]], num_tokens: l
 
 
 
-def named_apply(
-    fn: Callable,
-    module: nn.Module,
-    name: str = "",
-    depth_first: bool = True,
-    include_root: bool = False,
-) -> nn.Module:
-    """Apply fn to all submodules (in-place, no replacement)."""
-    if not depth_first and include_root:
-        fn(module=module, name=name)
-    for child_name, child_module in module.named_children():
-        child_name = ".".join((name, child_name)) if name else child_name
-        named_apply(
-            fn=fn,
-            module=child_module,
-            name=child_name,
-            depth_first=depth_first,
-            include_root=True,
-        )
-    if depth_first and include_root:
-        fn(module=module, name=name)
-    return module
-
-
 # ---- rms_norm ----
 
 
@@ -98,10 +74,6 @@ class RMSNorm(nn.Module):
         self.eps = eps
         self.weight = nn.Parameter(torch.ones(dim, device=device))
 
-    def reset_parameters(self) -> None:
-        """Reset weight to ones."""
-        nn.init.ones_(self.weight)
-
     def forward(self, x: Tensor) -> Tensor:
         """Apply RMS normalization."""
         rms = torch.sqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
@@ -140,10 +112,6 @@ class LayerScale(nn.Module):
         self.gamma = nn.Parameter(torch.empty(dim, device=device))
         self.init_values = init_values
 
-    def reset_parameters(self) -> None:
-        """Reset gamma to initial values."""
-        nn.init.constant_(self.gamma, self.init_values)
-
     def forward(self, x: Tensor) -> Tensor:
         """Apply per-channel scaling."""
         return x.mul_(self.gamma) if self.inplace else x * self.gamma
@@ -230,13 +198,6 @@ class PatchEmbed(nn.Module):
 
         return x
 
-    def reset_parameters(self) -> None:
-        """Reset Conv3d parameters with uniform initialization."""
-        k = 1 / (self.in_chans * self.tubelet_size * self.patch_size[0] * self.patch_size[1])
-        nn.init.uniform_(self.proj.weight, -math.sqrt(k), math.sqrt(k))
-        if self.proj.bias is not None:
-            nn.init.uniform_(self.proj.bias, -math.sqrt(k), math.sqrt(k))
-
 
 # ---- rope ----
 
@@ -850,25 +811,11 @@ import torch
 from torch import Tensor, nn
 
 
-torch._dynamo.config.automatic_dynamic_shapes = False
-torch._dynamo.config.accumulated_cache_size_limit = 1024
-# Per-code-object recompile cap (default 8). With dynamic=False + fullgraph=True,
-# every distinct input shape forces a static recompile of the block. Gram adds the
-# Gram-teacher forward at gram_teacher_crops_size (e.g. 768/1152) on top of the
-# 512/768 image + video + local-crop shapes, pushing the distinct-shape count past
-# 8 → FailOnRecompileLimitHit (hard crash, not the eager-fallback warning seen when
-# fullgraph=False). Raise the cap so all Gram shapes compile; the accumulated cap
-# (1024) still bounds total graphs. Only the shapes that actually occur are compiled,
-# so a high cap costs nothing when Gram is off.
-torch._dynamo.config.recompile_limit = 64
-
-
-
 class SelfAttentionBlock(nn.Module):
-    """Pre-norm transformer block: Norm -> Attention -> LayerScale -> DropPath -> Residual.
+    """Pre-norm transformer block: Norm -> Attention -> LayerScale -> Residual (x2).
 
     Supports both single-tensor and list-of-tensors forward for efficient multi-crop
-    processing during MOTIF training.
+    processing.
 
     Args:
         dim: Model dimension.
@@ -938,81 +885,17 @@ class SelfAttentionBlock(nn.Module):
         )
         self.ls2 = LayerScale(dim, init_values=init_values, device=device) if init_values else nn.Identity()
 
-        self.sample_drop_ratio = drop_path
-
-    @staticmethod
-    def _maybe_index_rope(
-        rope: tuple[Tensor, Tensor] | None,
-        indices: Tensor,
-    ) -> tuple[Tensor, Tensor] | None:
-        """Optionally index into RoPE embeddings for stochastic depth."""
-        if rope is None:
-            return None
-        sin, cos = rope
-        assert sin.ndim == cos.ndim
-        if sin.ndim == 4:
-            return sin[indices], cos[indices]
-        else:
-            return sin, cos
-
     def _forward_list(self, x_list: list[Tensor], rope_list: list | None = None) -> list[Tensor]:
-        """Forward pass for list of tensors with stochastic depth support.
+        """Forward pass for a list of tensors (one per crop), each with its own RoPE.
 
-        Concatenates tokens from multiple inputs for efficient elementwise operations,
-        then splits for per-input attention computation (different RoPE per crop).
+        Pre-norm residual: Norm -> Attention -> LayerScale -> Residual, twice (attn, ffn).
         """
-        b_list = [x.shape[0] for x in x_list]
-        sample_subset_sizes = [max(int(b * (1 - self.sample_drop_ratio)), 1) for b in b_list]
-        residual_scale_factors = [b / s for b, s in zip(b_list, sample_subset_sizes)]
-
-        if self.training and self.sample_drop_ratio > 0.0:
-            indices_1_list = [
-                (torch.randperm(b, device=x.device))[:s]
-                for x, b, s in zip(x_list, b_list, sample_subset_sizes)
-            ]
-            x_subset_1_list = [x[idx] for x, idx in zip(x_list, indices_1_list)]
-
-            if rope_list is not None:
-                rope_subset_list = [
-                    self._maybe_index_rope(rope, idx) for rope, idx in zip(rope_list, indices_1_list)
-                ]
-            else:
-                rope_subset_list = rope_list
-
-            norm1 = [self.norm1(x) for x in x_subset_1_list]
-            residual_1_list = self.attn.forward_list(norm1, rope_list=rope_subset_list)
-
-            x_attn_list = [
-                torch.index_add(
-                    x, dim=0, source=self.ls1(r), index=idx, alpha=scale,
-                )
-                for x, r, idx, scale in zip(x_list, residual_1_list, indices_1_list, residual_scale_factors)
-            ]
-
-            indices_2_list = [
-                (torch.randperm(b, device=x.device))[:s]
-                for x, b, s in zip(x_list, b_list, sample_subset_sizes)
-            ]
-            x_subset_2_list = [x[idx] for x, idx in zip(x_attn_list, indices_2_list)]
-            norm2_list = [self.norm2(x) for x in x_subset_2_list]
-
-            residual_2_list = self.mlp.forward_list(norm2_list)
-
-            x_ffn = [
-                torch.index_add(
-                    xa, dim=0, source=self.ls2(r), index=idx, alpha=scale,
-                )
-                for xa, r, idx, scale in zip(x_attn_list, residual_2_list, indices_2_list, residual_scale_factors)
-            ]
-        else:
-            x_out = []
-            for x, rope in zip(x_list, rope_list):
-                x_attn = x + self.ls1(self.attn(self.norm1(x), rope=rope))
-                x_ffn_item = x_attn + self.ls2(self.mlp(self.norm2(x_attn)))
-                x_out.append(x_ffn_item)
-            x_ffn = x_out
-
-        return x_ffn
+        x_out = []
+        for x, rope in zip(x_list, rope_list):
+            x_attn = x + self.ls1(self.attn(self.norm1(x), rope=rope))
+            x_ffn_item = x_attn + self.ls2(self.mlp(self.norm2(x_attn)))
+            x_out.append(x_ffn_item)
+        return x_out
 
     def forward(
         self,
@@ -1046,7 +929,6 @@ from functools import partial
 from typing import Any
 
 import torch
-import torch.nn.init
 from torch import Tensor, nn
 
 
@@ -1072,33 +954,6 @@ dtype_dict: dict[str, torch.dtype] = {
 }
 
 
-def init_weights_vit(module: nn.Module, name: str = "") -> None:
-    """Initialize weights for ViT components.
-
-    Applied recursively via named_apply to all submodules.
-
-    Args:
-        module: Module to initialize.
-        name: Module name (for logging, unused).
-    """
-    if isinstance(module, nn.Linear):
-        torch.nn.init.trunc_normal_(module.weight, std=0.02)
-        if module.bias is not None:
-            nn.init.zeros_(module.bias)
-        if hasattr(module, "bias_mask") and module.bias_mask is not None:
-            o = module.out_features
-            module.bias_mask.fill_(1)
-            module.bias_mask[o // 3 : 2 * o // 3].fill_(0)
-    if isinstance(module, nn.LayerNorm):
-        module.reset_parameters()
-    if isinstance(module, LayerScale):
-        module.reset_parameters()
-    if isinstance(module, PatchEmbed):
-        module.reset_parameters()
-    if isinstance(module, RMSNorm):
-        module.reset_parameters()
-
-
 class MotifVisionTransformer(nn.Module):
     """Vision Transformer backbone with 3D RoPE for unified image/video processing.
 
@@ -1106,9 +961,8 @@ class MotifVisionTransformer(nn.Module):
     - PatchEmbed (Conv3d) for unified image/video tokenization
     - Full 3D axial RoPE positional encoding (T/H/W)
     - CLS token + register (storage) tokens
-    - LayerScale and stochastic depth (DropPath)
+    - LayerScale
     - MLP or SwiGLU FFN variants
-    - FSDP-compatible (SHARD_GRAD_OP strategy)
 
     Token sequence layout: [CLS] + [Register x n_storage_tokens] + [Patch x N_total]
 
@@ -1255,15 +1109,6 @@ class MotifVisionTransformer(nn.Module):
         self.head = nn.Identity()
         self.mask_token = nn.Parameter(torch.empty(1, embed_dim, device=device))
 
-    def init_weights(self) -> None:
-        """Initialize all model weights."""
-        self.rope_embed._init_weights()
-        nn.init.normal_(self.cls_token, std=0.02)
-        if self.n_storage_tokens > 0:
-            nn.init.normal_(self.storage_tokens, std=0.02)
-        nn.init.zeros_(self.mask_token)
-        named_apply(init_weights_vit, self)
-
     def prepare_tokens_with_masks(
         self,
         x: Tensor,