Initial model files and config for custom ELECTRA Large classifier for sentiment

README.md

@@ -1,3 +1,390 @@
 ---
 license: mit
+tags:
+- sentiment-analysis
+- text-classification
+- electra
+- pytorch
+- transformers
 ---
+
+# Electra Base Classifier for Sentiment Analysis
+
+This is an [ELECTRA large discriminator](https://huggingface.co/google/electra-large-discriminator) fine-tuned for sentiment analysis of reviews. It has a mean pooling layer and a classifier head (2 layers of 1024 dimension) with SwishGLU activation and dropout (0.3). It classifies text into three sentiment categories: 'negative' (0), 'neutral' (1), and 'positive' (2). It was fine-tuned on the [Sentiment Merged](https://huggingface.co/datasets/jbeno/sentiment_merged) dataset, which is a merge of Stanford Sentiment Treebank (SST-3), and DynaSent Rounds 1 and 2.
+
+
+## Labels
+
+The model predicts the following labels:
+
+- `0`: negative
+- `1`: neutral
+- `2`: positive
+
+## How to Use
+
+### Install package
+
+This model requires the classes in `electra_classifier.py`. You can download the file, or you can install the package from PyPI.
+
+```bash
+pip install electra-classifier
+```
+
+### Load classes and model
+```python
+# Install the package in a notebook
+!pip install electra-classifier
+
+# Import libraries
+import torch
+from transformers import AutoTokenizer
+from electra_classifier import ElectraClassifier
+
+# Load tokenizer and model
+model_name = "jbeno/electra-large-classifier-sentiment"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = ElectraClassifier.from_pretrained(model_name)
+
+# Set model to evaluation mode
+model.eval()
+
+# Run inference
+text = "I love this restaurant!"
+inputs = tokenizer(text, return_tensors="pt")
+
+with torch.no_grad():
+    logits = model(**inputs)
+    predicted_class_id = torch.argmax(logits, dim=1).item()
+    predicted_label = model.config.id2label[predicted_class_id]
+    print(f"Predicted label: {predicted_label}")
+```
+
+## Requirements
+- Python 3.7+
+- PyTorch
+- Transformers
+- [electra-classifier](https://pypi.org/project/electra-classifier/) - Install with pip, or download electra_classifier.py
+
+## Training Details
+
+### Dataset
+
+The model was trained on the [Sentiment Merged](https://huggingface.co/datasets/jbeno/sentiment_merged) dataset, which is a mix of Stanford Sentiment Treebank (SST-3), DynaSent Round 1, and DynaSent Round 2.
+
+### Code
+
+The code used to train the model can be found on GitHub:
+- [jbeno/sentiment](https://github.com/jbeno/sentiment)
+- [jbeno/electra-classifier](https://github.com/jbeno/electra-classifier)
+
+### Research Paper
+
+The research paper can be found here: [ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis](https://github.com/jbeno/sentiment/research_paper.pdf)
+
+### Performance Summary
+
+- **Merged Dataset**
+    - Macro Average F1: **82.36**
+    - Accuracy: **82.96**
+- **DynaSent R1**
+    - Macro Average F1: **85.91**
+    - Accuracy: **85.83**
+- **DynaSent R2**
+    - Macro Average F1: **76.29**
+    - Accuracy: **76.53**
+- **SST-3**
+    - Macro Average F1: **70.90**
+    - Accuracy: **80.36**
+
+## Model Architecture
+
+- **Base Model**: ELECTRA large discriminator (`google/electra-large-discriminator`)
+- **Pooling Layer**: Custom pooling layer supporting 'cls', 'mean', and 'max' pooling types.
+- **Classifier**: Custom classifier with configurable hidden dimensions, number of layers, and dropout rate.
+    - **Activation Function**: Custom SwishGLU activation function.
+
+```
+ElectraClassifier(
+  (electra): ElectraModel(
+    (embeddings): ElectraEmbeddings(
+      (word_embeddings): Embedding(30522, 1024, padding_idx=0)
+      (position_embeddings): Embedding(512, 1024)
+      (token_type_embeddings): Embedding(2, 1024)
+      (LayerNorm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True)
+      (dropout): Dropout(p=0.1, inplace=False)
+    )
+    (encoder): ElectraEncoder(
+      (layer): ModuleList(
+        (0-23): 24 x ElectraLayer(
+          (attention): ElectraAttention(
+            (self): ElectraSelfAttention(
+              (query): Linear(in_features=1024, out_features=1024, bias=True)
+              (key): Linear(in_features=1024, out_features=1024, bias=True)
+              (value): Linear(in_features=1024, out_features=1024, bias=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+            (output): ElectraSelfOutput(
+              (dense): Linear(in_features=1024, out_features=1024, bias=True)
+              (LayerNorm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (intermediate): ElectraIntermediate(
+            (dense): Linear(in_features=1024, out_features=4096, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): ElectraOutput(
+            (dense): Linear(in_features=4096, out_features=1024, bias=True)
+            (LayerNorm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True)
+            (dropout): Dropout(p=0.1, inplace=False)
+          )
+        )
+      )
+    )
+  )
+  (custom_pooling): PoolingLayer()
+  (classifier): Classifier(
+    (layers): Sequential(
+      (0): Linear(in_features=1024, out_features=1024, bias=True)
+      (1): SwishGLU(
+        (projection): Linear(in_features=1024, out_features=2048, bias=True)
+        (activation): SiLU()
+      )
+      (2): Dropout(p=0.3, inplace=False)
+      (3): Linear(in_features=1024, out_features=1024, bias=True)
+      (4): SwishGLU(
+        (projection): Linear(in_features=1024, out_features=2048, bias=True)
+        (activation): SiLU()
+      )
+      (5): Dropout(p=0.3, inplace=False)
+      (6): Linear(in_features=1024, out_features=3, bias=True)
+    )
+  )
+)
+```
+
+## Custom Model Components
+
+### SwishGLU Activation Function
+
+The SwishGLU activation function combines the Swish activation with a Gated Linear Unit (GLU). It enhances the model's ability to capture complex patterns in the data.
+
+```python
+class SwishGLU(nn.Module):
+    def __init__(self, input_dim: int, output_dim: int):
+        super(SwishGLU, self).__init__()
+        self.projection = nn.Linear(input_dim, 2 * output_dim)
+        self.activation = nn.SiLU()
+
+    def forward(self, x):
+        x_proj_gate = self.projection(x)
+        projected, gate = x_proj_gate.tensor_split(2, dim=-1)
+        return projected * self.activation(gate)
+```
+
+### PoolingLayer
+
+The PoolingLayer class allows you to choose between different pooling strategies:
+
+- `cls`: Uses the representation of the \[CLS\] token.
+- `mean`: Calculates the mean of the token embeddings.
+- `max`: Takes the maximum value across token embeddings.
+
+**'mean'** pooling was used in the fine-tuned model.
+
+```python
+class PoolingLayer(nn.Module):
+    def __init__(self, pooling_type='cls'):
+        super().__init__()
+        self.pooling_type = pooling_type
+
+    def forward(self, last_hidden_state, attention_mask):
+        if self.pooling_type == 'cls':
+            return last_hidden_state[:, 0, :]
+        elif self.pooling_type == 'mean':
+            return (last_hidden_state * attention_mask.unsqueeze(-1)).sum(1) / attention_mask.sum(-1).unsqueeze(-1)
+        elif self.pooling_type == 'max':
+            return torch.max(last_hidden_state * attention_mask.unsqueeze(-1), dim=1)[0]
+        else:
+            raise ValueError(f"Unknown pooling method: {self.pooling_type}")
+```
+
+### Classifier
+
+The Classifier class is a customizable feed-forward neural network used for the final classification.
+
+The fine-tuned model had:
+
+- `input_dim`: 1024
+- `num_layers`: 2
+- `hidden_dim`: 1024
+- `hidden_activation`: SwishGLU
+- `dropout_rate`: 0.3
+- `n_classes`: 3
+
+```python
+class Classifier(nn.Module):
+    def __init__(self, input_dim, hidden_dim, hidden_activation, num_layers, n_classes, dropout_rate=0.0):
+        super().__init__()
+        layers = []
+        layers.append(nn.Linear(input_dim, hidden_dim))
+        layers.append(hidden_activation)
+        if dropout_rate > 0:
+            layers.append(nn.Dropout(dropout_rate))
+
+        for _ in range(num_layers - 1):
+            layers.append(nn.Linear(hidden_dim, hidden_dim))
+            layers.append(hidden_activation)
+            if dropout_rate > 0:
+                layers.append(nn.Dropout(dropout_rate))
+
+        layers.append(nn.Linear(hidden_dim, n_classes))
+        self.layers = nn.Sequential(*layers)
+```
+
+## Model Configuration
+
+The model's configuration (config.json) includes custom parameters:
+
+- `hidden_dim`: Size of the hidden layers in the classifier.
+- `hidden_activation`: Activation function used in the classifier ('SwishGLU').
+- `num_layers`: Number of layers in the classifier.
+- `dropout_rate`: Dropout rate used in the classifier.
+- `pooling`: Pooling strategy used ('mean').
+
+## Performance by Dataset
+
+### Merged Dataset
+
+```
+Merged Dataset Classification Report
+
+              precision    recall  f1-score   support
+
+    negative   0.858503  0.843537  0.850954      2352
+     neutral   0.747684  0.750137  0.748908      1829
+    positive   0.864513  0.877395  0.870906      2349
+
+    accuracy                       0.829556      6530
+   macro avg   0.823567  0.823690  0.823590      6530
+weighted avg   0.829626  0.829556  0.829549      6530
+
+ROC AUC: 0.947247
+
+Predicted  negative  neutral  positive
+Actual                                
+negative       1984      256       112
+neutral         246     1372       211
+positive         81      207      2061
+
+Macro F1 Score: 0.82
+```
+
+### DynaSent Round 1
+
+```
+DynaSent Round 1 Classification Report
+
+              precision    recall  f1-score   support
+
+    negative   0.913204  0.824167  0.866404      1200
+     neutral   0.779433  0.915833  0.842146      1200
+    positive   0.905149  0.835000  0.868661      1200
+
+    accuracy                       0.858333      3600
+   macro avg   0.865929  0.858333  0.859070      3600
+weighted avg   0.865929  0.858333  0.859070      3600
+
+ROC AUC: 0.963133
+
+Predicted  negative  neutral  positive
+Actual                                
+negative        989      156        55
+neutral          51     1099        50
+positive         43      155      1002
+
+Macro F1 Score: 0.86
+```
+
+### DynaSent Round 2
+
+```
+DynaSent Round 2 Classification Report
+
+              precision    recall  f1-score   support
+
+    negative   0.764706  0.812500  0.787879       240
+     neutral   0.814815  0.641667  0.717949       240
+    positive   0.731884  0.841667  0.782946       240
+
+    accuracy                       0.765278       720
+   macro avg   0.770468  0.765278  0.762924       720
+weighted avg   0.770468  0.765278  0.762924       720
+
+ROC AUC: 0.927688
+
+Predicted  negative  neutral  positive
+Actual                                
+negative        195       19        26
+neutral          38      154        48
+positive         22       16       202
+
+Macro F1 Score: 0.76
+```
+
+### Stanford Sentiment Treebank (SST-3)
+
+```
+SST-3 Classification Report
+
+              precision    recall  f1-score   support
+
+    negative   0.822199  0.877193  0.848806       912
+     neutral   0.504237  0.305913  0.380800       389
+    positive   0.856144  0.942794  0.897382       909
+
+    accuracy                       0.803620      2210
+   macro avg   0.727527  0.708633  0.708996      2210
+weighted avg   0.780194  0.803620  0.786409      2210
+
+ROC AUC: 0.904787
+
+Predicted  negative  neutral  positive
+Actual                                
+negative        800       81        31
+neutral         157      119       113
+positive         16       36       857
+
+Macro F1 Score: 0.71
+```
+
+## License
+
+This model is licensed under the MIT License.
+
+## Citation
+
+If you use this model in your work, please consider citing it:
+
+```bibtex
+@misc{beno-2024-electra_base_classifier_sentiment,
+  title={Electra Large Classifier for Sentiment Analysis},
+  author={Jim Beno},
+  year={2024},
+  publisher={Hugging Face},
+  howpublished={\url{https://huggingface.co/jbeno/electra-large-classifier-sentiment}},
+}
+```
+
+## Contact
+
+For questions or comments, please open an issue on the repository or contact [Jim Beno](https://huggingface.co/jbeno).
+
+## Acknowledgments
+
+- The [Hugging Face Transformers library](https://github.com/huggingface/transformers) for providing powerful tools for model development.
+- The creators of the [ELECTRA model](https://arxiv.org/abs/2003.10555) for their foundational work.
+- The authors of the datasets used: [Stanford Sentiment Treebank](https://huggingface.co/datasets/stanfordnlp/sst), [DynaSent](https://huggingface.co/datasets/dynabench/dynasent).
+- [Stanford Engineering CGOE](https://cgoe.stanford.edu), [Chris Potts](https://stanford.edu/~cgpotts/), and the Course Facilitators of [XCS224U](https://online.stanford.edu/courses/xcs224u-natural-language-understanding)
+

config.json

@@ -0,0 +1,44 @@
+{
+  "architectures": [
+    "ElectraClassifier"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dropout_rate": 0.3,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_activation": "SwishGLU",
+  "hidden_dim": 1024,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_layers": 2,
+  "pad_token_id": 0,
+  "pooling": "mean",
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

electra_classifier.py

@@ -0,0 +1,96 @@
+import torch
+from torch import nn
+from transformers import ElectraPreTrainedModel, ElectraModel
+
+# Custom activation function
+class SwishGLU(nn.Module):
+    def __init__(self, input_dim: int, output_dim: int):
+        super(SwishGLU, self).__init__()
+        self.projection = nn.Linear(input_dim, 2 * output_dim)
+        self.activation = nn.SiLU()
+
+    def forward(self, x):
+        x_proj_gate = self.projection(x)
+        projected, gate = x_proj_gate.tensor_split(2, dim=-1)
+        return projected * self.activation(gate)
+
+
+# Custom pooling layer
+class PoolingLayer(nn.Module):
+    def __init__(self, pooling_type='cls'):
+        super().__init__()
+        self.pooling_type = pooling_type
+
+    def forward(self, last_hidden_state, attention_mask):
+        if self.pooling_type == 'cls':
+            return last_hidden_state[:, 0, :]
+        elif self.pooling_type == 'mean':
+            # Mean pooling over the token embeddings
+            return (last_hidden_state * attention_mask.unsqueeze(-1)).sum(1) / attention_mask.sum(-1).unsqueeze(-1)
+        elif self.pooling_type == 'max':
+            # Max pooling over the token embeddings
+            return torch.max(last_hidden_state * attention_mask.unsqueeze(-1), dim=1)[0]
+        else:
+            raise ValueError(f"Unknown pooling method: {self.pooling_type}")
+
+
+# Custom classifier
+class Classifier(nn.Module):
+    def __init__(self, input_dim, hidden_dim, hidden_activation, num_layers, n_classes, dropout_rate=0.0):
+        super().__init__()
+        layers = []
+        layers.append(nn.Linear(input_dim, hidden_dim))
+        layers.append(hidden_activation)
+        if dropout_rate > 0:
+            layers.append(nn.Dropout(dropout_rate))
+
+        for _ in range(num_layers - 1):
+            layers.append(nn.Linear(hidden_dim, hidden_dim))
+            layers.append(hidden_activation)
+            if dropout_rate > 0:
+                layers.append(nn.Dropout(dropout_rate))
+
+        layers.append(nn.Linear(hidden_dim, n_classes))
+        self.layers = nn.Sequential(*layers)
+
+    def forward(self, x):
+        return self.layers(x)
+
+
+# Custom Electra classifier model
+class ElectraClassifier(ElectraPreTrainedModel):
+    def __init__(self, config):
+        super().__init__(config)
+        self.electra = ElectraModel(config)
+
+        if hasattr(self.electra, 'pooler'):
+            self.electra.pooler = None
+
+        self.pooling = PoolingLayer(pooling_type=config.pooling)
+
+        # Handle custom activation functions
+        activation_name = config.hidden_activation
+        if activation_name == 'SwishGLU':
+            hidden_activation = SwishGLU(
+                input_dim=config.hidden_dim,
+                output_dim=config.hidden_dim
+            )
+        else:
+            activation_class = getattr(nn, activation_name)
+            hidden_activation = activation_class()
+
+        self.classifier = Classifier(
+            input_dim=config.hidden_size,
+            hidden_dim=config.hidden_dim,
+            hidden_activation=hidden_activation,
+            num_layers=config.num_layers,
+            n_classes=config.num_labels,
+            dropout_rate=config.dropout_rate
+        )
+        self.init_weights()
+
+    def forward(self, input_ids=None, attention_mask=None, **kwargs):
+        outputs = self.electra(input_ids, attention_mask=attention_mask, **kwargs)
+        pooled_output = self.pooling(outputs.last_hidden_state, attention_mask)
+        logits = self.classifier(pooled_output)
+        return logits

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf9a8ff41dc560d132c6430079e745cffd96e9cfe23c6100022c1bf68ba0b0
+size 1353223676

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f138e3d706d1972f0859d0f0385a19c98ac2713c9a9ff8f13f28494986d402c
+size 1353307070

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}