nbroad
commited on
Commit
•
f23f112
1
Parent(s):
4400790
commit files to HF hub
Browse files- README.md +58 -0
- config.json +82 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- text-classification
|
6 |
+
- bert
|
7 |
+
- pytorch
|
8 |
+
license: apache-2.0
|
9 |
+
widget:
|
10 |
+
- text: "In fiscal year 2019, we reduced our comprehensive carbon footprint for the fourth consecutive year—down 35 percent compared to 2015, when Apple’s carbon emissions peaked, even as net revenue increased by 11 percent over that same period. In the past year, we avoided over 10 million metric tons from our emissions reduction initiatives—like our Supplier Clean Energy Program, which lowered our footprint by 4.4 million metric tons. "
|
11 |
+
example_title: "Carbon Footprint"
|
12 |
+
---
|
13 |
+
|
14 |
+
# ESG BERT
|
15 |
+
|
16 |
+
(Uploaded from https://github.com/mukut03/ESG-BERT)
|
17 |
+
|
18 |
+
**Domain Specific BERT Model for Text Mining in Sustainable Investing**
|
19 |
+
|
20 |
+
Read more about this pre-trained model [here.](https://towardsdatascience.com/nlp-meets-sustainable-investing-d0542b3c264b?source=friends_link&sk=1f7e6641c3378aaff319a81decf387bf)
|
21 |
+
|
22 |
+
**In collaboration with [Charan Pothireddi](https://www.linkedin.com/in/sree-charan-pothireddi-6a0a3587/) and [Parabole.ai](https://www.linkedin.com/in/sree-charan-pothireddi-6a0a3587/)**
|
23 |
+
|
24 |
+
|
25 |
+
### Labels
|
26 |
+
|
27 |
+
0: Business_Ethics
|
28 |
+
1: Data_Security
|
29 |
+
2: Access_And_Affordability
|
30 |
+
3: Business_Model_Resilience
|
31 |
+
4: Competitive_Behavior
|
32 |
+
5: Critical_Incident_Risk_Management
|
33 |
+
6: Customer_Welfare
|
34 |
+
7: Director_Removal
|
35 |
+
8: Employee_Engagement_Inclusion_And_Diversity
|
36 |
+
9: Employee_Health_And_Safety
|
37 |
+
10: Human_Rights_And_Community_Relations
|
38 |
+
11: Labor_Practices
|
39 |
+
12: Management_Of_Legal_And_Regulatory_Framework
|
40 |
+
13: Physical_Impacts_Of_Climate_Change
|
41 |
+
14: Product_Quality_And_Safety
|
42 |
+
15: Product_Design_And_Lifecycle_Management
|
43 |
+
16: Selling_Practices_And_Product_Labeling
|
44 |
+
17: Supply_Chain_Management
|
45 |
+
18: Systemic_Risk_Management
|
46 |
+
19: Waste_And_Hazardous_Materials_Management
|
47 |
+
20: Water_And_Wastewater_Management
|
48 |
+
21: Air_Quality
|
49 |
+
22: Customer_Privacy
|
50 |
+
23: Ecological_Impacts
|
51 |
+
24: Energy_Management
|
52 |
+
25: GHG_Emissions
|
53 |
+
|
54 |
+
|
55 |
+
### References:
|
56 |
+
[1] - ---
|
57 |
+
|
58 |
+
https://medium.com/analytics-vidhya/deploy-huggingface-s-bert-to-production-with-pytorch-serve-27b068026d18
|
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": ".",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Business_Ethics",
|
14 |
+
"1": "Data_Security",
|
15 |
+
"2": "Access_And_Affordability",
|
16 |
+
"3": "Business_Model_Resilience",
|
17 |
+
"4": "Competitive_Behavior",
|
18 |
+
"5": "Critical_Incident_Risk_Management",
|
19 |
+
"6": "Customer_Welfare",
|
20 |
+
"7": "Director_Removal",
|
21 |
+
"8": "Employee_Engagement_Inclusion_And_Diversity",
|
22 |
+
"9": "Employee_Health_And_Safety",
|
23 |
+
"10": "Human_Rights_And_Community_Relations",
|
24 |
+
"11": "Labor_Practices",
|
25 |
+
"12": "Management_Of_Legal_And_Regulatory_Framework",
|
26 |
+
"13": "Physical_Impacts_Of_Climate_Change",
|
27 |
+
"14": "Product_Quality_And_Safety",
|
28 |
+
"15": "Product_Design_And_Lifecycle_Management",
|
29 |
+
"16": "Selling_Practices_And_Product_Labeling",
|
30 |
+
"17": "Supply_Chain_Management",
|
31 |
+
"18": "Systemic_Risk_Management",
|
32 |
+
"19": "Waste_And_Hazardous_Materials_Management",
|
33 |
+
"20": "Water_And_Wastewater_Management",
|
34 |
+
"21": "Air_Quality",
|
35 |
+
"22": "Customer_Privacy",
|
36 |
+
"23": "Ecological_Impacts",
|
37 |
+
"24": "Energy_Management",
|
38 |
+
"25": "GHG_Emissions"
|
39 |
+
},
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"label2id": {
|
43 |
+
"Access_And_Affordability": 2,
|
44 |
+
"Air_Quality": 21,
|
45 |
+
"Business_Ethics": 0,
|
46 |
+
"Business_Model_Resilience": 3,
|
47 |
+
"Competitive_Behavior": 4,
|
48 |
+
"Critical_Incident_Risk_Management": 5,
|
49 |
+
"Customer_Privacy": 22,
|
50 |
+
"Customer_Welfare": 6,
|
51 |
+
"Data_Security": 1,
|
52 |
+
"Director_Removal": 7,
|
53 |
+
"Ecological_Impacts": 23,
|
54 |
+
"Employee_Engagement_Inclusion_And_Diversity": 8,
|
55 |
+
"Employee_Health_And_Safety": 9,
|
56 |
+
"Energy_Management": 24,
|
57 |
+
"GHG_Emissions": 25,
|
58 |
+
"Human_Rights_And_Community_Relations": 10,
|
59 |
+
"Labor_Practices": 11,
|
60 |
+
"Management_Of_Legal_And_Regulatory_Framework": 12,
|
61 |
+
"Physical_Impacts_Of_Climate_Change": 13,
|
62 |
+
"Product_Design_And_Lifecycle_Management": 15,
|
63 |
+
"Product_Quality_And_Safety": 14,
|
64 |
+
"Selling_Practices_And_Product_Labeling": 16,
|
65 |
+
"Supply_Chain_Management": 17,
|
66 |
+
"Systemic_Risk_Management": 18,
|
67 |
+
"Waste_And_Hazardous_Materials_Management": 19,
|
68 |
+
"Water_And_Wastewater_Management": 20
|
69 |
+
},
|
70 |
+
"layer_norm_eps": 1e-12,
|
71 |
+
"max_position_embeddings": 512,
|
72 |
+
"model_type": "bert",
|
73 |
+
"num_attention_heads": 12,
|
74 |
+
"num_hidden_layers": 12,
|
75 |
+
"pad_token_id": 0,
|
76 |
+
"position_embedding_type": "absolute",
|
77 |
+
"torch_dtype": "float32",
|
78 |
+
"transformers_version": "4.14.1",
|
79 |
+
"type_vocab_size": 2,
|
80 |
+
"use_cache": true,
|
81 |
+
"vocab_size": 30522
|
82 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa781011a42ba2f73e0293c53fda580e5fcd03169380634ae07752c78eb9259
|
3 |
+
size 438090221
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": ".", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|