2000 steps checkpoint

README.md

@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+language:
+- en
+- vi
+metrics:
+- f1
+base_model:
+- distilbert/distilbert-base-multilingual-cased
+pipeline_tag: text-classification
+tags:
+- finance
+- esg
+- financial-text-analysis
+- bert
+library_name: transformers
+widget:
+- text: "Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation."
+---
+
+ESG analysis can help investors determine a business' long-term sustainability and identify associated risks. ViDistilBERT-ESG-base is a [https://huggingface.co/distilbert/distilbert-base-multilingual-cased](distilbert/distilbert-base-multilingual-cased) model fine-tuned on [https://huggingface.co/nguyen599/ViEn-ESG-100](ViEn-ESG-100) dataset, include 100,000 annotated sentences from Vietnam, English news and ESG reports.  
+
+**Input**: A financial text.
+
+**Output**: Environmental, Social, Governance or None.
+
+**Language support**: English, Vietnamese
+
+# How to use 
+You can use this model with Transformers pipeline for ESG classification.
+```python
+# tested in transformers==4.51.0 
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+
+esgbert = AutoModelForSequenceClassification.from_pretrained('nguyen599/ViDistilBERT-ESG-base',num_labels=4)
+tokenizer = AutoTokenizer.from_pretrained('nguyen599/ViDistilBERT-ESG-base')
+nlp = pipeline("text-classification", model=esgbert, tokenizer=tokenizer)
+results = nlp('Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation.')
+print(results) # [{'label': 'Environment', 'score': 0.9206041026115417}]
+
+```

config.json

@@ -0,0 +1,37 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Neural",
+    "1": "Environmental",
+    "2": "Social",
+    "3": "Governance"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": "Neural",
+    "1": "Environmental",
+    "2": "Social",
+    "3": "Governance"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dad68a045706014d00957a42fd4c030f36f15dc87faa2b3b0e5e5d0556da67a
+size 541323528

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": false,
+  "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]"
+}