shanmukhdatta commited on
Commit
19601b7
·
verified ·
1 Parent(s): e61011d

Initial model release for RiskPulse AI

Browse files
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: mit
5
+ tags:
6
+ - financial
7
+ - event-classification
8
+ - bert
9
+ - finbert
10
+ - riskpulse
11
+ datasets:
12
+ - financial_news
13
+ metrics:
14
+ - accuracy
15
+ - f1
16
+ pipeline_tag: text-classification
17
+ ---
18
+
19
+ # RiskPulse AI — 5-Class Financial Event Classifier
20
+
21
+ Fine-tuned transformer model for financial event classification as part of the **RiskPulse AI** Financial Risk Intelligence system (S&P Global & CRISIL Campus Hackathon 2026).
22
+
23
+ ## Classes
24
+ 1. **Geopolitical**
25
+ 2. **Macroeconomic**
26
+ 3. **Credit Event**
27
+ 4. **Merger / Acquisition**
28
+ 5. **Product Launch**
29
+
30
+ ## Architecture & Base Model
31
+ - Architecture: FinBERT / BERT Sequence Classification with 5 target classes.
32
+ - Weights: Safetensors checkpoint included.
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "return_dict": true,
3
+ "output_hidden_states": false,
4
+ "torchscript": false,
5
+ "dtype": null,
6
+ "pruned_heads": {},
7
+ "tie_word_embeddings": true,
8
+ "chunk_size_feed_forward": 0,
9
+ "is_encoder_decoder": false,
10
+ "is_decoder": false,
11
+ "cross_attention_hidden_size": null,
12
+ "add_cross_attention": false,
13
+ "tie_encoder_decoder": false,
14
+ "architectures": [
15
+ "BertForSequenceClassification"
16
+ ],
17
+ "finetuning_task": null,
18
+ "id2label": {
19
+ "0": "Geopolitical",
20
+ "1": "Macroeconomic",
21
+ "2": "Credit Event",
22
+ "3": "Merger / Acquisition",
23
+ "4": "Product Launch"
24
+ },
25
+ "label2id": {
26
+ "Geopolitical": 0,
27
+ "Macroeconomic": 1,
28
+ "Credit Event": 2,
29
+ "Merger / Acquisition": 3,
30
+ "Product Launch": 4
31
+ },
32
+ "task_specific_params": null,
33
+ "problem_type": "single_label_classification",
34
+ "tokenizer_class": null,
35
+ "prefix": null,
36
+ "bos_token_id": null,
37
+ "pad_token_id": 0,
38
+ "eos_token_id": null,
39
+ "sep_token_id": null,
40
+ "decoder_start_token_id": null,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "do_sample": false,
44
+ "early_stopping": false,
45
+ "num_beams": 1,
46
+ "temperature": 1.0,
47
+ "top_k": 50,
48
+ "top_p": 1.0,
49
+ "typical_p": 1.0,
50
+ "repetition_penalty": 1.0,
51
+ "length_penalty": 1.0,
52
+ "no_repeat_ngram_size": 0,
53
+ "encoder_no_repeat_ngram_size": 0,
54
+ "bad_words_ids": null,
55
+ "num_return_sequences": 1,
56
+ "output_scores": false,
57
+ "return_dict_in_generate": false,
58
+ "forced_bos_token_id": null,
59
+ "forced_eos_token_id": null,
60
+ "remove_invalid_values": false,
61
+ "exponential_decay_length_penalty": null,
62
+ "suppress_tokens": null,
63
+ "begin_suppress_tokens": null,
64
+ "num_beam_groups": 1,
65
+ "diversity_penalty": 0.0,
66
+ "_name_or_path": "yiyanghkust/finbert-tone",
67
+ "transformers_version": "4.57.6",
68
+ "tf_legacy_loss": false,
69
+ "use_bfloat16": false,
70
+ "vocab_size": 30873,
71
+ "hidden_size": 768,
72
+ "num_hidden_layers": 12,
73
+ "num_attention_heads": 12,
74
+ "hidden_act": "gelu",
75
+ "intermediate_size": 3072,
76
+ "hidden_dropout_prob": 0.1,
77
+ "attention_probs_dropout_prob": 0.1,
78
+ "max_position_embeddings": 512,
79
+ "type_vocab_size": 2,
80
+ "initializer_range": 0.02,
81
+ "layer_norm_eps": 1e-12,
82
+ "position_embedding_type": "absolute",
83
+ "use_cache": true,
84
+ "classifier_dropout": null,
85
+ "model_type": "bert",
86
+ "output_attentions": false,
87
+ "num_labels": 5
88
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30c77aa93be94f03df24965851ff1457cdf56e941a0d277bf700bf93a974cea
3
+ size 439046148
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "2": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff