Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,12 @@
+{
+  "architectures": [
+    "EncoderModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_encoder.EncoderConfig",
+    "AutoModel": "modelling_encoder.EncoderModel"
+  },
+  "model_type": "openvla_encoder",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2"
+}

configuration_encoder.py

@@ -0,0 +1,13 @@
+from transformers import PretrainedConfig
+from typing import List
+
+
+
+class EncoderConfig(PretrainedConfig):
+    model_type = "openvla_encoder"
+
+    def __init__(
+        self,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded54c6da7a723a8d90136d8ac8c60f802e0d146a253657df1159eabc8ef4532
+size 1212959392

modelling_encoder.py

@@ -0,0 +1,76 @@
+import torch
+import torch.nn as nn
+import timm
+import torch
+import torch.nn as nn
+from transformers import PreTrainedModel
+from timm.models.vision_transformer import LayerScale
+from functools import partial
+from typing import Any, Callable, Tuple
+from transformers import PreTrainedModel
+from .configuration_encoder import EncoderConfig
+
+
+
+# === Utility Functions for Monkey-Patching ===
+def _ls_new_forward(self, x: torch.Tensor) -> torch.Tensor:
+    """
+    Patch LayerScale forward method to use scale_factor instead of gamma.
+    """
+    return x.mul_(self.scale_factor) if self.inplace else x * self.scale_factor
+
+
+def ls_apply_patch(ls_module: LayerScale):
+    """
+    Apply the LayerScale patch to replace gamma with scale_factor.
+    """
+    ls_module.scale_factor = nn.Parameter(ls_module.gamma.clone())
+    ls_module.forward = _ls_new_forward.__get__(ls_module, LayerScale)
+    del ls_module.gamma
+
+def unpack_tuple(fn: Callable[[Any], Tuple[Any]]) -> Callable[[Any], Any]:
+    """
+    Utility function to unpack tuple results from the model's intermediate layers.
+    """
+    def wrapper(*args: Any, **kwargs: Any) -> Any:
+        result = fn(*args, **kwargs)
+        return result[0] if isinstance(result, tuple) else result
+
+    return wrapper
+
+class EncoderModel(PreTrainedModel):
+    """
+    Custom Vision Transformer Encoder based on timm's Vision Transformer.
+    """
+    config_class = EncoderConfig
+    def __init__(self, config):
+        """
+        Initializes the model. No configurable parameters as it's tied to specific weights.
+        """
+        super().__init__(config)
+        self.encoder = timm.create_model(
+            "vit_large_patch14_reg4_dinov2.lvd142m",
+            img_size=224,
+            num_classes=0,
+            pretrained=False
+        )
+
+        # Apply LayerScale patch
+        for module in self.encoder.modules():
+            if isinstance(module, LayerScale):
+                ls_apply_patch(module)
+
+        # Patch forward method to return specific intermediate layers
+        self.encoder.forward = unpack_tuple(
+            partial( self.encoder.get_intermediate_layers, n={len(self.encoder.blocks) - 2})
+        )
+
+    def forward(self, pixel_values: torch.Tensor) -> torch.Tensor:
+        """
+        Forward pass for the vision encoder.
+        Args:
+            pixel_values (torch.Tensor): Input tensor of shape (batch_size, channels, height, width).
+        Returns:
+            torch.Tensor: The output embeddings.
+        """
+        return self.encoder.forward(pixel_values)