Upload folder using huggingface_hub

README.md

@@ -1,68 +1,57 @@
 ---
-library_name: transformers
+language: en
 tags:
-- generated_from_trainer
-model-index:
-- name: bert-reg-biencoder-mse
-  results: []
+- bert
+- regression
+- biencoder
+- similarity
+pipeline_tag: text-similarity
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# bert-reg-biencoder-mse
-
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0817
-- Mse: 0.0812
-- Mae: 0.2278
-- Pearson Corr: 0.2835
-- Spearman Corr: 0.2331
-- Cosine Sim: 0.9097
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 7
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Mse    | Mae    | Pearson Corr | Spearman Corr | Cosine Sim |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------------:|:-------------:|:----------:|
-| 0.1219        | 1.0   | 21   | 0.1124          | 0.1117 | 0.2560 | 0.1406       | 0.0993        | 0.9055     |
-| 0.1017        | 2.0   | 42   | 0.0838          | 0.0833 | 0.2248 | 0.1312       | 0.1239        | 0.9045     |
-| 0.0872        | 3.0   | 63   | 0.0778          | 0.0775 | 0.2205 | 0.2520       | 0.1374        | 0.9097     |
-| 0.0694        | 4.0   | 84   | 0.0860          | 0.0856 | 0.2328 | 0.1923       | 0.1456        | 0.9037     |
-| 0.0533        | 5.0   | 105  | 0.0958          | 0.0951 | 0.2418 | 0.3089       | 0.2252        | 0.9132     |
-| 0.0478        | 6.0   | 126  | 0.0782          | 0.0778 | 0.2216 | 0.2913       | 0.2325        | 0.9096     |
-| 0.0385        | 7.0   | 147  | 0.0817          | 0.0812 | 0.2278 | 0.2835       | 0.2331        | 0.9097     |
-
-
-### Framework versions
-
-- Transformers 4.45.1
-- Pytorch 2.4.0
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+# BiEncoder Regression Model
+
+This model is a BiEncoder architecture that outputs similarity scores between text pairs.
+
+## Model Details
+- Base Model: bert-base-uncased
+- Task: Regression
+- Architecture: BiEncoder with cosine similarity
+- Loss Function: mse
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModel
+from modeling import BiEncoderModelRegression
+
+# Load model components
+tokenizer = AutoTokenizer.from_pretrained("minoosh/bert-reg-biencoder-mse")
+base_model = AutoModel.from_pretrained("bert-base-uncased")
+model = BiEncoderModelRegression(base_model, loss_fn="mse")
+
+# Load weights
+state_dict = torch.load("pytorch_model.bin")
+model.load_state_dict(state_dict)
+
+# Prepare inputs
+texts1 = ["first text"]
+texts2 = ["second text"]
+inputs = tokenizer(
+    texts1, texts2,
+    padding=True,
+    truncation=True,
+    return_tensors="pt"
+)
+
+# Get similarity scores
+outputs = model(**inputs)
+similarity_scores = outputs["logits"]
+```
+
+## Metrics
+The model was trained using mse loss and evaluated using:
+- Mean Squared Error (MSE)
+- Mean Absolute Error (MAE)
+- Pearson Correlation
+- Spearman Correlation
+- Cosine Similarity