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 +1,19 @@
+{
+  "_name_or_path": "DeepTranslateAdmin/wmt22-cometkiwi-da",
+  "activations": "Tanh",
+  "architectures": [
+    "CometModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_comet.CometModelConfig",
+    "AutoModel": "modeling_comet.CometModel"
+  },
+  "dropout": 0.1,
+  "hidden_sizes": [
+    3072,
+    1024
+  ],
+  "model_type": "comet",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1"
+}

configuration_comet.py

@@ -0,0 +1,17 @@
+from transformers import PretrainedConfig
+
+
+class CometModelConfig(PretrainedConfig):
+    model_type = "comet"
+
+    def __init__(
+        self,
+        hidden_sizes=[3072, 1024],
+        activations="Tanh",
+        dropout=0.1,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.hidden_sizes = hidden_sizes
+        self.activations = activations
+        self.dropout = dropout

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84b3af475a5f997e62b24a0bb618633d32fa54785531acd216ac6184b79fd9e
+size 2260603844

modeling_comet.py

@@ -0,0 +1,152 @@
+from typing import Any
+
+import torch
+from torch import nn
+from transformers import (
+    PreTrainedModel,
+    XLMRobertaConfig,
+    XLMRobertaModel,
+)
+from .configuration_comet import CometModelConfig
+
+
+class Encoder(nn.Module):
+    """Encoder module based on XLMRoberta."""
+
+    def __init__(self):
+        super().__init__()
+        self.model = XLMRobertaModel(
+            config=XLMRobertaConfig.from_pretrained("microsoft/infoxlm-large"),
+            add_pooling_layer=False,
+        )
+        self.model.encoder.output_hidden_states = True
+
+    def forward(
+        self, input_ids: torch.Tensor, attention_mask: torch.Tensor, **kwargs: Any
+    ) -> dict[str, Any]:
+        return self.model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            output_hidden_states=True,
+            return_dict=False,
+        )[-1]
+
+    @property
+    def num_layers(self) -> int:
+        """Number of model layers available."""
+        return self.model.config.num_hidden_layers + 1
+
+    @property
+    def output_units(self) -> int:
+        """Max number of tokens the encoder handles."""
+        return self.model.config.hidden_size
+
+
+class LayerwiseAttention(nn.Module):
+    """Module that applies attention across model layers."""
+
+    def __init__(
+        self,
+        num_layers: int,
+        layer_weights: list[float] | None = None,
+    ) -> None:
+        super().__init__()
+        layer_weights = layer_weights or [0.0] * num_layers
+        self.scalar_parameters = nn.ParameterList(
+            [
+                nn.Parameter(torch.HalfTensor([layer_weights[i]]), requires_grad=True)
+                for i in range(num_layers)
+            ]
+        )
+        self.weight = nn.Parameter(torch.HalfTensor([1.0]), requires_grad=True)
+
+    def forward(
+        self,
+        tensors: list[torch.Tensor],
+        mask: torch.Tensor,
+    ) -> torch.Tensor:
+        weights = torch.cat([parameter for parameter in self.scalar_parameters])
+        normed_weights = torch.softmax(weights, dim=0)
+        normed_weights = torch.split(normed_weights, split_size_or_sections=1)
+        return self.weight * sum(
+            weight * tensor for weight, tensor in zip(normed_weights, tensors)
+        )
+
+
+class Estimator(nn.Module):
+    """Feed-forward estimator module."""
+
+    def _get_activation(self, activation: str) -> nn.Module:
+        """Get activation function by name."""
+        if hasattr(nn, activation.title()):
+            return getattr(nn, activation.title())()
+        raise ValueError(f"{activation} is not a valid activation function!")
+
+    def __init__(
+        self,
+        in_dim: int,
+        out_dim: int = 1,
+        hidden_sizes: list[int] = [3072, 1024],
+        activations: str = "Tanh",
+        dropout: float = 0.1,
+    ) -> None:
+        super().__init__()
+        modules: list[nn.Module] = []
+
+        # First layer
+        modules.append(nn.Linear(in_dim, hidden_sizes[0]))
+        modules.append(self._get_activation(activations))
+        modules.append(nn.Dropout(dropout))
+
+        # Hidden layers
+        for i in range(1, len(hidden_sizes)):
+            modules.append(nn.Linear(hidden_sizes[i - 1], hidden_sizes[i]))
+            modules.append(self._get_activation(activations))
+            modules.append(nn.Dropout(dropout))
+
+        # Output layer
+        modules.append(nn.Linear(hidden_sizes[-1], int(out_dim)))
+
+        self.ff = nn.Sequential(*modules)
+
+    def forward(self, in_features: torch.Tensor) -> torch.Tensor:
+        return self.ff(in_features)
+
+
+class CometModel(PreTrainedModel):
+    config_class = CometModelConfig
+    _no_split_modules = ["Encoder", "LayerwiseAttention", "Estimator"]
+
+    def __init__(self, config: CometModelConfig) -> None:
+        super().__init__(config)
+
+        self.encoder = Encoder()
+        self.layerwise_attention = LayerwiseAttention(
+            num_layers=self.encoder.num_layers
+        )
+        self.estimator = Estimator(
+            in_dim=self.encoder.output_units,
+            hidden_sizes=config.hidden_sizes,
+            activations=config.activations,
+            dropout=config.dropout,
+        )
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        attention_mask: torch.Tensor,
+        token_type_ids: torch.Tensor | None = None,
+        **kwargs: Any,
+    ) -> torch.Tensor:
+        encoder_out = self.encoder(
+            input_ids,
+            attention_mask,
+            token_type_ids=token_type_ids,
+        )
+        embeddings = self.layerwise_attention(
+            encoder_out,
+            attention_mask,
+        )
+        # Use CLS token as sentence embedding
+        embedding = embeddings[:, 0, :]
+        return self.estimator(embedding).view(-1)