File size: 7,195 Bytes
a58b94a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 |
from transformers import PretrainedConfig
from typing import List, Dict
class ESGifyConfig(PretrainedConfig):
model_type = "mpnet"
def __init__(
self,
attention_probs_dropout_prob: float = 0.1,
bos_token_id: int = 0,
eos_token_id: int = 2,
hidden_act: str = "gelu",
hidden_dropout_prob: float = 0.1,
hidden_size: int = 768,
initializer_range: float = 0.02,
intermediate_size: int = 3072,
layer_norm_eps: float = 1e-05,
max_position_embeddings: int = 514,
num_attention_heads: int = 12,
num_hidden_layers: int = 12,
output_attentions: bool = True,
pad_token_id: int = 1,
relative_attention_num_buckets: int = 32,
vocab_size: int = 30531,
id2label: Dict = {"0": "Legal Proceedings & Law Violations",
"1": "Biodiversity",
"2": "Communities Health and Safety",
"3": "Land Acquisition and Resettlement (S)",
"4": "Emergencies (Social)",
"5": "Corporate Governance",
"6": "Responsible Investment & Greenwashing",
"7": "Not Relevant to ESG",
"8": "Economic Crime",
"9": "Emergencies (Environmental)",
"10": "Hazardous Materials Management",
"11": "Environmental Management",
"12": "Landscape Transformation",
"13": "Human Rights",
"14": "Climate Risks",
"15": "Labor Relations Management",
"16": "Freedom of Association and Right to Organise",
"17": "Employee Health and Safety",
"18": "Surface Water Pollution",
"19": "Animal Welfare",
"20": "Water Consumption",
"21": "Disclosure",
"22": "Product Safety and Quality",
"23": "Greenhouse Gas Emissions",
"24": "Indigenous People",
"25": "Cultural Heritage",
"26": "Air Pollution",
"27": "Waste Management",
"28": "Soil and Groundwater Impact",
"29": "Forced Labour",
"30": "Wastewater Management",
"31": "Natural Resources",
"32": "Physical Impacts",
"33": "Values and Ethics",
"34": "Risk Management and Internal Control",
"35": "Supply Chain (Environmental)",
"36": "Supply Chain (Social)",
"37": "Discrimination",
"38": "Minimum Age and Child Labour",
"39": "Planning Limitations",
"40": "Data Safety",
"41": "Strategy Implementation",
"42": "Energy Efficiency and Renewables",
"43": "Land Acquisition and Resettlement (E)",
"44": "Supply Chain (Economic / Governance)",
"45": "Land Rehabilitation",
"46": "Retrenchment"
},
label2id: Dict = {"Legal Proceedings & Law Violations": "0",
"Biodiversity": "1",
"Communities Health and Safety": "2",
"Land Acquisition and Resettlement (S)": "3",
"Emergencies (Social)": "4",
"Corporate Governance": "5",
"Responsible Investment & Greenwashing": "6",
"Not Relevant to ESG": "7",
"Economic Crime": "8",
"Emergencies (Environmental)": "9",
"Hazardous Materials Management": "10",
"Environmental Management": "11",
"Landscape Transformation": "12",
"Human Rights": "13",
"Climate Risks": "14",
"Labor Relations Management": "15",
"Freedom of Association and Right to Organise": "16",
"Employee Health and Safety": "17",
"Surface Water Pollution": "18",
"Animal Welfare": "19",
"Water Consumption": "20",
"Disclosure": "21",
"Product Safety and Quality": "22",
"Greenhouse Gas Emissions": "23",
"Indigenous People": "24",
"Cultural Heritage": "25",
"Air Pollution": "26",
"Waste Management": "27",
"Soil and Groundwater Impact": "28",
"Forced Labour": "29",
"Wastewater Management": "30",
"Natural Resources": "31",
"Physical Impacts": "32",
"Values and Ethics": "33",
"Risk Management and Internal Control": "34",
"Supply Chain (Environmental)": "35",
"Supply Chain (Social)": "36",
"Discrimination": "37",
"Minimum Age and Child Labour": "38",
"Planning Limitations": "39",
"Data Safety": "40",
"Strategy Implementation": "41",
"Energy Efficiency and Renewables": "42",
"Land Acquisition and Resettlement (E)": "43",
"Supply Chain (Economic / Governance)": "44",
"Land Rehabilitation": "45",
"Retrenchment": "46"},
**kwargs,
):
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.bos_token_id = bos_token_id,
self.eos_token_id = eos_token_id,
self.hidden_act = hidden_act,
self.hidden_dropout_prob = hidden_dropout_prob,
self.hidden_size = hidden_size,
self.initializer_range = initializer_range,
self.intermediate_size = intermediate_size,
self.layer_norm_eps = layer_norm_eps
self.max_position_embeddings = max_position_embeddings,
self.num_attention_heads = num_attention_heads,
self.num_hidden_layers = num_hidden_layers,
self.output_attentions = output_attentions,
self.pad_token_id = pad_token_id,
self.relative_attention_num_buckets = relative_attention_num_buckets,
self.vocab_size = vocab_size,
self.id2label = id2label,
self.label2id = label2id
super().__init__(**kwargs) |