Update README and model files

.gitattributes

@@ -0,0 +1 @@
+*.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,57 @@
+# 🧠 DistilBERT Response Type Classifier
+
+This is a fine-tuned [DistilBERT](https://huggingface.co/distilbert-base-uncased) model designed to classify patient messages into one of four mental health support categories:
+
+- **advice**
+- **information**
+- **question**
+- **validation**
+
+It is used as part of the [Mental Health Counselor Assistant](https://huggingface.co/spaces/scdong/counselor-assistant) app to help generate helpful, therapeutic responses.
+
+## 💼 Use Case
+
+Given a short text input from a patient, this model predicts the most appropriate **type of response** a mental health counselor might provide.
+
+### Example:
+```python
+from transformers import DistilBertForSequenceClassification, DistilBertTokenizerFast
+import torch
+
+model = DistilBertForSequenceClassification.from_pretrained("scdong/distilbert-response-type")
+tokenizer = DistilBertTokenizerFast.from_pretrained("scdong/distilbert-response-type")
+
+text = "I just feel so overwhelmed lately"
+inputs = tokenizer(text, return_tensors="pt")
+with torch.no_grad():
+    logits = model(**inputs).logits
+
+predicted_label = torch.argmax(logits, dim=1).item()
+print(predicted_label)  # Maps to: 0=advice, 1=information, 2=question, 3=validation
+```
+
+The model is used to route text to custom prompt templates like:
+- *Advice prompt*: “You are a licensed counselor. What supportive advice would you give to someone who said: {msg}?”
+- *Validation prompt*: “You are an empathetic therapist. Validate the client’s emotions in response to: {msg}”
+
+## 📁 Files
+
+This repo includes:
+- `config.json` — model architecture config
+- `model.safetensors` — trained model weights
+- `tokenizer_config.json`, `tokenizer.json`, `vocab.txt` — tokenizer files
+- `special_tokens_map.json` — optional token mappings
+- `training_args.bin` — training metadata (optional)
+
+## 🧪 Training Details
+
+The model was fine-tuned using a balanced dataset labeled with response types based on:
+- [Kaggle Mental Health Conversations](https://www.kaggle.com/datasets/ayaanalahmed/mental-health-conversations)
+- [CounselChat dataset](https://github.com/nbertagnolli/counsel-chat)
+- [PAIR dataset](https://lit.eecs.umich.edu/downloads.html#PAIR)
+
+The final model was validated on a held-out test set and integrated into the counselor assistant tool.
+
+## 📜 License
+
+This model is released under an open license for research and educational purposes. Please use responsibly and do not deploy for unsupervised clinical use.

config.json

@@ -0,0 +1,35 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf29c46c297b4f1cdf81a91225e0abe2ccc5add77a0d9a90409aac2d535ee22
+size 267838720

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]"
+}