automodel classifier

.gitignore

@@ -0,0 +1 @@
+.ipynb_checkpoints

README.md

@@ -1,9 +1,35 @@
+# DistilBERT Essay Scoring Model (Test)
+
+This model is a **proof-of-concept for automated essay scoring**, built using **DistilBERT** and integrated with the Hugging Face Hub through the [`PyTorchModelHubMixin`](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin).  
+It was trained for **only one epoch** and is intended **for testing pipeline integration**, not production use.
+
 ---
-tags:
-- model_hub_mixin
-- pytorch_model_hub_mixin
+
+## Task
+- **Automated Essay Scoring (Text Classification)**
+
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: [More Information Needed]
-- Docs: [More Information Needed]
+## Usage
+
+```python
+from transformers import DistilBertTokenizerFast
+from model import DistilBERTClassifier
+import torch
+
+# Load model and tokenizer
+model = DistilBERTClassifier.from_pretrained("melanchthon19/mews-aes-classifier-base")
+tokenizer = DistilBertTokenizerFast.from_pretrained("distilbert-base-uncased")
+
+# Example text
+text = "The essay demonstrates clear structure and coherent argumentation."
+
+# Tokenize
+inputs = tokenizer(text, truncation=True, padding='max_length', max_length=512, return_tensors="pt")
+
+# Predict
+with torch.no_grad():
+    logits = model(**inputs)
+    prediction = torch.argmax(logits, dim=1).item()
+
+print("Predicted score class:", prediction)

config.json

@@ -1,5 +1,5 @@
 {
   "freeze_params": true,
   "model_dir": "/Users/sunpn/.cache/huggingface/hub/models--distilbert-base-uncased/snapshots/12040accade4e8a0f71eabdb258fecc2e7e948be/",
-  "num_labels": 5
+  "num_labels": 10
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daeef9f59a1af43243b29a73a857f0ec3bed4a04c9a45594201ac791af543687
-size 265859740
+oid sha256:358c60ee387a23808f6978be79ab7512b8e96b62a78ce6a9eb40d5eafe69c387
+size 265862328

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}