Upload BertForStance

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]

bert_for_stance.py

@@ -0,0 +1,71 @@
+# STL
+from typing import Optional
+import dataclasses
+# 3rd Party
+import torch
+from transformers import BertPreTrainedModel, BertModel
+from transformers.models.bert.modeling_bert import BaseModelOutputWithPoolingAndCrossAttentions
+from transformers.utils.generic import ModelOutput
+# Local
+from .configuration_bert_for_stance import BertForStanceConfig
+
+
+class BertForStance(BertPreTrainedModel):
+    config_class = BertForStanceConfig
+
+    def __init__(self, config: BertForStanceConfig):
+        super().__init__(config)
+        self.config = config
+        self.num_labels = config.num_labels
+        self.bert = BertModel(config)
+        hidden_size = config.hidden_size
+        classifier_hidden_units = config.classifier_hidden_units or config.hidden_size
+        self.classifier = torch.nn.Sequential(
+            torch.nn.Dropout(config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob),
+            torch.nn.Linear(hidden_size, classifier_hidden_units, bias=True),
+            torch.nn.ReLU(),
+            torch.nn.Linear(classifier_hidden_units, self.num_labels, bias=True)
+        )
+        self.loss_fct = torch.nn.CrossEntropyLoss()
+        self.post_init()
+
+    @dataclasses.dataclass
+    class Output(ModelOutput):
+        loss: Optional[torch.FloatTensor] = None
+        logits: Optional[torch.FloatTensor] = None
+        seq_encoding: Optional[torch.FloatTensor] = None
+
+
+    def forward(
+         self,
+         input_ids: Optional[torch.Tensor] = None,
+         attention_mask: Optional[torch.Tensor] = None,
+         token_type_ids: Optional[torch.Tensor] = None,
+         position_ids: Optional[torch.Tensor] = None,
+         head_mask: Optional[torch.Tensor] = None,
+         inputs_embeds: Optional[torch.Tensor] = None,
+         labels: Optional[torch.Tensor] = None,
+         return_dict: Optional[bool] = None,
+     ):
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        outputs: BaseModelOutputWithPoolingAndCrossAttentions = self.bert(
+            input_ids,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            position_ids=position_ids,
+            head_mask=head_mask,
+            inputs_embeds=inputs_embeds,
+            output_attentions=False,
+            output_hidden_states=True,
+            return_dict=True,
+        )
+        feature_vec = outputs.last_hidden_state[:, 0]
+        logits = self.classifier(feature_vec)
+        loss = None
+        if labels is not None:
+           loss = self.loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
+        return BertForStance.Output(loss=loss, logits=logits, seq_encoding=feature_vec)
+
+BertForStance.register_for_auto_class("AutoModel")
+BertForStance.register_for_auto_class("AutoModelForSequenceClassification")

config.json

@@ -0,0 +1,32 @@
+{
+  "add_pooling_layer": false,
+  "architectures": [
+    "BertForStance"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "configuration_bert_for_stance.BertForStanceConfig",
+    "AutoModelForSequenceClassification": "bert_for_stance.BertForStance"
+  },
+  "classifier_dropout": null,
+  "classifier_hidden_units": 768,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert_for_stance",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

configuration_bert_for_stance.py

@@ -0,0 +1,16 @@
+from transformers.models.bert.configuration_bert import BertConfig
+from typing import Optional
+
+class BertForStanceConfig(BertConfig):
+    model_type = "bert_for_stance"
+    def __init__(self,
+                 *,
+                 classifier_hidden_units: Optional[int] = None,
+                 **base_kwargs):
+        super().__init__(**base_kwargs)
+        self.problem_type = "single_label_classification"
+        self.add_pooling_layer = False
+        self.return_dict = True
+        self.classifier_hidden_units = classifier_hidden_units if classifier_hidden_units else self.hidden_size
+
+BertForStanceConfig.register_for_auto_class("AutoConfig")

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aca18447f51d9fa758b83e4826d29c69f0a39cd0fb0ff88f5414952d3217224
+size 440321200