first commit

README.md

@@ -1,3 +1,30 @@
 ---
-license: apache-2.0
+language: 
+- zh
+tags:
+- bert
+license: "apache-2.0"
 ---
+
+# Financial Sentiment Analysis in Chinese
+This is a fine-tuned version of FinBERT, based on [bert-base-chinese](https://huggingface.co/bert-base-chinese), on a private dataset (around ~8k analyst report sentences) for sentiment analysis. 
+
+* Test Accuracy = 0.88
+* Test Macro F1 = 0.87  
+* **Labels**: 0 -> Neutral; 1 -> Positive; 2 -> Negative
+
+# Usage
+```
+from transformers import TextClassificationPipeline
+from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
+from transformers import BertTokenizerFast
+model_path="./fin_sentiment_bert_zh/"
+new_model = AutoModelForSequenceClassification.from_pretrained(model_path,output_attentions=True)
+tokenizer = BertTokenizerFast.from_pretrained(model_path)
+PipelineInterface = TextClassificationPipeline(model=new_model, tokenizer=tokenizer, return_all_scores=True)
+label = PipelineInterface("此外宁德时代上半年实现出口约2GWh，同比增加200%+。") 
+print(label)
+```
+```
+[[{'label': 'LABEL_0', 'score': 0.0007030126871541142}, {'label': 'LABEL_1', 'score': 0.9989339709281921}, {'label': 'LABEL_2', 'score': 0.000363016442861408}]]
+```

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "bert-base-chinese",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c25b105902f90d1e039d511944af4f49d1490f6698e701f2704a714ca74e66b
+size 409103316

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 +1,57 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}