Upload Vietnamese sentiment analysis model

README.md

@@ -0,0 +1,73 @@
+---
+language: vi
+license: mit
+tags:
+- vietnamese
+- sentiment-analysis
+- phobert
+- text-classification
+datasets:
+- custom
+metrics:
+- f1
+---
+
+# Vietnamese Sentiment Analysis Model
+
+This model is fine-tuned from [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) for Vietnamese sentiment analysis with entity context.
+
+## Model description
+
+The model classifies text sentiment into three categories:
+- NEGATIVE (0)
+- NEUTRAL (1)
+- POSITIVE (2)
+
+It is specifically designed to analyze sentiment toward a specific entity mentioned in the text.
+
+## Intended uses & limitations
+
+The model is intended to be used for Vietnamese sentiment analysis, specifically when analyzing sentiment toward a named entity.
+
+### How to use
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Khoa/vietnamese-sentiment-analysis-with-entity")
+model = AutoModelForSequenceClassification.from_pretrained("Khoa/vietnamese-sentiment-analysis-with-entity")
+
+# Function to predict sentiment
+def predict_sentiment(text, entity, model, tokenizer):
+    combined_text = f"Đối với {entity}, {text}"
+    inputs = tokenizer(combined_text, return_tensors="pt", truncation=True, padding=True)
+    
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        predicted_class = torch.argmax(predictions, dim=-1).item()
+    
+    sentiment_labels = {0: "NEGATIVE", 1: "NEUTRAL", 2: "POSITIVE"}
+    return sentiment_labels[predicted_class], predictions[0].tolist()
+
+# Example usage
+text = "Món ăn rất ngon nhưng giá hơi đắt"
+entity = "Nhà hàng ABC"
+sentiment, confidence = predict_sentiment(text, entity, model, tokenizer)
+print(f"Sentiment: {sentiment}")
+```
+
+## Training procedure
+
+The model was fine-tuned on a custom Vietnamese dataset with entity-specific sentiment annotations.
+
+
+This model was fine-tuned on a custom Vietnamese sentiment analysis dataset.
+It achieves the following metrics on the test set:
+- Accuracy: 0.0000
+- F1 Score: 0.0000
+- Precision: 0.0000
+- Recall: 0.0000
+

added_tokens.json

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

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "vinai/phobert-base",
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.48.3",
+  "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:abbe45d0304b45cfc244c963ad7cc5850f2003dcbf7f31f4287284964c29fa45
+size 540026460

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>"
+}