3000 steps checkpoint

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+language:
+- en
+- vi
+metrics:
+- f1
+base_model:
+- ProsusAI/finbert
+pipeline_tag: fill-mask
+tags:
+- finance
+- esg
+- text-classification
+- fill-mask
+library_name: transformers
+datasets:
+- nguyen599/ViEn-ESG-100
+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. MaskESG-finbert-base is a [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) 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 Neural.
+
+**Language support**: English, Vietnamese
+
+# How to use
+You can use this model with Transformers pipeline for ESG classification or fill mask task.
+```python
+# tested in transformers==4.53.0
+from transformers import AutoTokenizer, AutoModelForMaskedLM, pipeline
+
+maskesg = AutoModelForMaskedLM.from_pretrained('nguyen599/MaskESG-finbert-base')
+tokenizer = AutoTokenizer.from_pretrained('nguyen599/MaskESG-finbert-base')
+nlp = pipeline("fill-mask", model=maskesg, tokenizer=tokenizer)
+# Classification as fill-mask
+results = nlp(f'Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation. This sentence is {tokenizer.mask_token}')
+print(results)
+# [{'score': 0.9015821814537048,
+#   'token': 444,
+#   'token_str': ' E',
+#   'sequence': 'Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation. This sentence is E'},
+#  {'score': 0.09723947197198868,
+#   'token': 427,
+#   'token_str': ' N',
+#   'sequence': 'Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation. This sentence is N'},
+#  {'score': 0.0010556845227256417,
+#   'token': 322,
+#   'token_str': ' S',
+#   'sequence': 'Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation. This sentence is S'},
+#  {'score': 0.0001152529803221114,
+#   'token': 443,
+#   'token_str': ' G',
+#   'sequence': 'Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation. This sentence is G'},
+#  {'score': 1.14425779429439e-06,
+#   'token': 299,
+#   'token_str': ' e',
+#   'sequence': 'Over three chapters, it covers a range of topics from energy efficiency and renewable energy to the circular economy and sustainable transportation. This sentence is e'}]
+
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "positive",
+    "1": "negative",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 1,
+    "neutral": 2,
+    "positive": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4112552086847f128dc12e96009d968e3f845d2839377a92948b0a19defb57
+size 219052380

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 +1,58 @@
+{
+  "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": true,
+  "extra_special_tokens": {},
+  "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]"
+}