2000 steps checkpoint

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+language:
+- en
+- vi
+metrics:
+- f1
+base_model:
+- FacebookAI/xlm-roberta-base
+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. ViXML-RoBERTa-ESG-base is a [https://huggingface.co/FacebookAI/xlm-roberta-base](FacebookAI/xlm-roberta-base) 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/ViXML-RoBERTa-ESG-base',num_labels=4)
+tokenizer = AutoTokenizer.from_pretrained('nguyen599/ViXML-RoBERTa-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 +1,40 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4374af0f9cac10ae977bf13fa2097fbc31a0b1219a016aba4ec8573b356627a
+size 1112211160

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}