Duplicate from wonrax/phobert-base-vietnamese-sentiment

Co-authored-by: Ha Huy Long Hai <wonrax@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,47 @@
+---
+language:
+- vi
+tags:
+- sentiment
+- classification
+license: mit
+widget:
+- text: "Không thể nào đẹp hơn"
+- text: "Quá phí tiền, mà không đẹp"
+- text: "Cái này giá ổn không nhỉ?"
+
+---
+
+[**GitHub Homepage**](https://github.com/wonrax/phobert-base-vietnamese-sentiment)
+
+A model fine-tuned for sentiment analysis based on [vinai/phobert-base](https://huggingface.co/vinai/phobert-base).
+
+Labels:
+- NEG: Negative
+- POS: Positive
+- NEU: Neutral
+
+Dataset: [30K e-commerce reviews](https://www.kaggle.com/datasets/linhlpv/vietnamese-sentiment-analyst)
+
+## Usage
+```python
+import torch
+from transformers import RobertaForSequenceClassification, AutoTokenizer
+
+model = RobertaForSequenceClassification.from_pretrained("wonrax/phobert-base-vietnamese-sentiment")
+
+tokenizer = AutoTokenizer.from_pretrained("wonrax/phobert-base-vietnamese-sentiment", use_fast=False)
+
+# Just like PhoBERT: INPUT TEXT MUST BE ALREADY WORD-SEGMENTED!
+sentence = 'Đây là mô_hình rất hay , phù_hợp với điều_kiện và như cầu của nhiều người .'  
+
+input_ids = torch.tensor([tokenizer.encode(sentence)])
+
+with torch.no_grad():
+    out = model(input_ids)
+    print(out.logits.softmax(dim=-1).tolist())
+    # Output:
+    # [[0.002, 0.988, 0.01]]
+    #     ^      ^      ^
+    #    NEG    POS    NEU
+```

added_tokens.json

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

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/thesis/models/ecomm-review-phobert-base-5epochs",
+  "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": "NEG",
+    "1": "POS",
+    "2": "NEU"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEG": 0,
+    "NEU": 2,
+    "POS": 1
+  },
+  "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": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09addc0848350e599eaba524a84fadd1339d1be8b96e724338c5804f8eb8b40
+size 540069101

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 256, "special_tokens_map_file": null, "name_or_path": "vinai/phobert-base", "tokenizer_class": "PhobertTokenizer"}