Upload folder using huggingface_hub

README.md

@@ -1,72 +1,74 @@
 ---
-library_name: transformers
+
+language: en
+
 tags:
-- generated_from_trainer
-metrics:
-- accuracy
-- f1
-- precision
-- recall
-model-index:
-- name: bert-clf-biencoder-focal_loss
-  results: []
+
+- bert
+
+- classification
+
+- pytorch
+
+pipeline_tag: text-classification
+
 ---
 
-<!-- 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-clf-biencoder-focal_loss
 
-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: 0.1136
-- Accuracy: 0.6602
-- F1: 0.6596
-- Precision: 0.6642
-- Recall: 0.6602
+# BiEncoder Classification Model
+
+
+
+This model is a BiEncoder architecture based on BERT for text pair classification.
+
+
+
+## Model Details
+
+- Base Model: bert-base-uncased
+
+- Architecture: BiEncoder with BERT base
+
+- Number of classes: 4
+
+
+
+## Usage
+
+
+
+```python
+
+from transformers import AutoTokenizer
+
+import torch
+
+
+
+# Load tokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("minoosh/bert-clf-biencoder-focal_loss")
 
-## Model description
 
-More information needed
 
-## Intended uses & limitations
+# Load model weights
 
-More information needed
+state_dict = torch.load("pytorch_model.bin")
 
-## Training and evaluation data
 
-More information needed
 
-## Training procedure
+# Initialize model (you'll need the BiEncoderModel class)
 
-### Training hyperparameters
+model = BiEncoderModel(
 
-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
+    base_model=AutoModel.from_pretrained("bert-base-uncased"),
 
-### Training results
+    num_classes=4
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.1571        | 1.0   | 78   | 0.1334          | 0.5761   | 0.5597 | 0.5846    | 0.5761 |
-| 0.1019        | 2.0   | 156  | 0.1009          | 0.6472   | 0.6399 | 0.6660    | 0.6472 |
-| 0.0711        | 3.0   | 234  | 0.0923          | 0.6861   | 0.6869 | 0.6910    | 0.6861 |
-| 0.0475        | 4.0   | 312  | 0.0972          | 0.6602   | 0.6611 | 0.6746    | 0.6602 |
-| 0.0258        | 5.0   | 390  | 0.1085          | 0.6602   | 0.6596 | 0.6699    | 0.6602 |
-| 0.0188        | 6.0   | 468  | 0.1099          | 0.6634   | 0.6626 | 0.6667    | 0.6634 |
-| 0.0155        | 7.0   | 546  | 0.1136          | 0.6602   | 0.6596 | 0.6642    | 0.6602 |
+)
 
+model.load_state_dict(state_dict)
 
-### Framework versions
+```
 
-- Transformers 4.45.1
-- Pytorch 2.4.0
-- Datasets 3.0.1
-- Tokenizers 0.20.0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78bb827ef654b29463de591a76cee89af85277cf87f9d3b9e1929eb3ece1d6c
+oid sha256:89a4316b804c5a8cb4debd7db680a72c6c626be8a99d7e09a6b092e97660e359
 size 438038894