Upload folder using huggingface_hub

README.md

@@ -26,10 +26,10 @@ model-index:
       name: Orality Regression
     metrics:
     - type: mae
-      value: 0.0819
+      value: 0.0791
       name: Mean Absolute Error
     - type: r2
-      value: 0.734
+      value: 0.748
       name: R² Score
 ---
 
@@ -48,26 +48,37 @@ Given a passage of text, the model outputs a continuous score where higher value
 | Task | Single-value regression (MSE loss) |
 | Output range | Continuous (not clamped) |
 | Max sequence length | 512 tokens |
-| Best MAE | **0.0819** |
-| R² (at best MAE) | **0.734** |
+| Best MAE | **0.0791** |
+| R² (at best MAE) | **0.748** |
 | Parameters | ~149M |
 
 ## Usage
 ```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import os
+os.environ["TORCH_COMPILE_DISABLE"] = "1"
+
+import warnings
+warnings.filterwarnings("ignore", message="Flash Attention 2 only supports")
+
 import torch
+from transformers import AutoModel, AutoTokenizer
 
 model_name = "HavelockAI/bert-orality-regressor"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
+model.eval()
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model = model.to(device)
 
 text = "Tell me, O Muse, of that ingenious hero who travelled far and wide"
 inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+inputs = {k: v.to(device) for k, v in inputs.items()}
 
-with torch.no_grad():
+with torch.no_grad(), torch.autocast(device_type=device.type, enabled=device.type == "cuda"):
     score = model(**inputs).logits.squeeze().item()
 
-print(f"Orality score: {score:.3f}")
+print(f"Orality score: {max(0.0, min(1.0, score)):.3f}")
 ```
 
 ### Score Interpretation
@@ -107,26 +118,26 @@ An 80/20 train/test split was used (random seed 42).
 
 | Epoch | Loss | MAE | R² |
 |-------|------|-----|-----|
-| 1 | 0.3485 | 0.1151 | 0.485 |
-| 2 | 0.0269 | 0.1145 | 0.446 |
-| 3 | 0.0235 | 0.0962 | 0.636 |
-| 4 | 0.0162 | 0.0937 | 0.648 |
-| 5 | 0.0228 | 0.1099 | 0.566 |
-| 6 | 0.0153 | 0.0971 | 0.605 |
-| 7 | 0.0115 | 0.0883 | 0.707 |
-| 8 | 0.0112 | 0.0906 | 0.681 |
-| 9 | 0.0095 | 0.0872 | 0.713 |
-| 10 | 0.0076 | 0.0898 | 0.691 |
-| 11 | 0.0060 | 0.0840 | 0.727 |
-| 12 | 0.0054 | 0.0850 | 0.715 |
-| 13 | 0.0050 | 0.0821 | 0.738 |
-| 14 | 0.0043 | 0.0820 | 0.737 |
-| **15** | **0.0040** | **0.0819** | **0.734** |
-| 16 | 0.0041 | 0.0891 | 0.689 |
-| 17 | 0.0035 | 0.0829 | 0.727 |
-| 18 | 0.0031 | 0.0825 | 0.729 |
-| 19 | 0.0032 | 0.0831 | 0.725 |
-| 20 | 0.0033 | 0.0833 | 0.724 |
+| 1 | 0.3496 | 0.1173 | 0.476 |
+| 2 | 0.0286 | 0.0992 | 0.593 |
+| 3 | 0.0215 | 0.0872 | 0.704 |
+| 4 | 0.0144 | 0.0879 | 0.714 |
+| 5 | 0.0169 | 0.0865 | 0.712 |
+| 6 | 0.0117 | 0.0853 | 0.700 |
+| 7 | 0.0096 | 0.0922 | 0.691 |
+| 8 | 0.0094 | 0.0850 | 0.722 |
+| 9 | 0.0086 | 0.0822 | 0.745 |
+| 10 | 0.0064 | 0.0841 | 0.723 |
+| 11 | 0.0054 | 0.0921 | 0.682 |
+| 12 | 0.0050 | 0.0840 | 0.720 |
+| 13 | 0.0044 | 0.0806 | 0.744 |
+| 14 | 0.0037 | 0.0805 | 0.740 |
+| **15** | **0.0034** | **0.0791** | **0.748** |
+| 16 | 0.0033 | 0.0807 | 0.738 |
+| 17 | 0.0031 | 0.0803 | 0.742 |
+| 18 | 0.0026 | 0.0797 | 0.745 |
+| 19 | 0.0027 | 0.0803 | 0.742 |
+| 20 | 0.0029 | 0.0805 | 0.741 |
 
 </details>