2000 steps checkpoint

README.md

@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+language:
+- en
+- vi
+metrics:
+- f1
+base_model:
+- microsoft/deberta-v3-small
+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. ViDeBERTa-v3-ESG-small is a [https://huggingface.co/microsoft/deberta-v3-small](microsoft/deberta-v3-small) model fine-tuned on [ViEn-ESG-100](https://huggingface.co/nguyen599/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/ViDeBERTa-v3-ESG-small',num_labels=4)
+tokenizer = AutoTokenizer.from_pretrained('nguyen599/ViDeBERTa-v3-ESG-small')
+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}]
+
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Neural",
+    "1": "Environmental",
+    "2": "Social",
+    "3": "Governance"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Environmental": 1,
+    "Governance": 3,
+    "Neural": 0,
+    "Social": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f04b1211be2b2779e7afef11b09bc94b5f98591de27e845a81b4373039a56522
+size 567604704

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}