upload file

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+tags:
+  - text-classification
+  - sentiment-analysis
+  - vietnamese
+  - vsfc
+  - phobert
+language:
+  - vi
+datasets:
+  - uit-vsfc
+model-index:
+  - name: VSFC Sentiment Classifier (PhoBERT)
+    results:
+      - task:
+          type: text-classification
+          name: Sentiment Analysis
+        dataset:
+          name: UIT-VSFC
+          type: uit-vsfc
+        metrics:
+          - type: accuracy
+            value: 85.3
+          - type: f1
+            value: 84.7
+---
+
+# VSFC Sentiment Classifier using PhoBERT
+
+This model is fine-tuned from [`vinai/phobert-base`](https://huggingface.co/vinai/phobert-base) on the UIT-VSFC dataset for Vietnamese sentiment analysis.
+
+## 🧠 Model Details
+
+- **Model type**: Transformer (BERT-based)
+- **Base model**: [`vinai/phobert-base`](https://huggingface.co/vinai/phobert-base)
+- **Fine-tuned task**: Sentence-level sentiment classification
+- **Target labels**: Positive, Negative, Neutral
+- **Tokenizer**: SentencePiece BPE
+
+## 📚 Training Data
+
+- **Dataset**: [UIT-VSFC](https://drive.google.com/drive/folders/1xclbjHHK58zk2X6iqbvMPS2rcy9y9E0X)
+- **Language**: Vietnamese
+- **License**: Academic use
+- Students’ feedback is a vital resource for the interdisciplinary research involving the combining of two different research fields between sentiment analysis and education.
+
+## 🚀 How to Use
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("tmt3103/VSFC-sentiment-classify-phoBERT")
+model = AutoModelForSequenceClassification.from_pretrained("tmt3103/VSFC-sentiment-classify-phoBERT")
+
+inputs = tokenizer("Giảng viên thân thiện dễ thương", return_tensors="pt")
+outputs = model(**inputs)
+predicted_class = outputs.logits.argmax(dim=-1).item()

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb4d0f31150e4bf6488b0f8eb28c0f272d624b1a08190dba31f2b4e977980ae
+size 540029536

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}