Add model

README.md

@@ -1,3 +1,35 @@
 ---
 license: apache-2.0
 ---
+
+# Model card for 
+
+## Model Description
+climateBUG-LM is a deep learning language model fine-tuned for analyzing bank reports in the context of climate change and sustainability. It leverages a unique annotated corpus, climateBUG-Data, which consists of statements from EU banks' annual and sustainability reports, focusing on climate change and finance. This model aims to classify statements as relevant or irrelevant to climate-related subjects, offering enhanced performance due to its domain-specific training.
+
+
+## Applications
+The model is ideal for:
++ Analyzing financial reports for climate change-related content.
++ Research in financial sustainability and climate economics.
++ Tracking how banks articulate their climate-related activities.
+
+## Limitations
++ Optimized for EU bank reports; performance may vary for other regions.
++ Primarily focused on climate and finance domains.
+
+## Citation
+Please cite this model as follows:
+
+Yu, Y., Scheidegger, S., Elliott, J., & Löfgren, Å. (2024). climateBUG: A data-driven framework for analyzing bank reporting through a climate lens. Expert Systems With Applications, 239, 122162.
+
+```bibtex
+@article{yu2024climatebug,
+title = {climateBUG : A data-driven framework for analyzing bank reporting through a climate lens},
+journal = {Expert Systems with Applications},
+volume = {239},
+pages = {122162},
+year = {2024},
+author = {Yinan Yu and Samuel Scheidegger and Jasmine Elliott and Åsa Löfgren}
+}
+```

model/added_tokens.json

@@ -0,0 +1 @@
+{"Reduce": 50301, "Denmark": 50352, "investing": 50276, "Principles for Responsible Investment": 50323, "Paris Agreement": 50285, "OP Financial": 50374, "energy efficiency": 50312, "ABN AMRO": 50341, "EU Green Deal": 50288, "fleet cars": 50315, "sustainable finance": 50266, "societal impact": 50269, "Helaba": 50414, "alignment": 50388, "Banco Sabadell": 50412, "RBI": 50418, "UN Global Compact": 50319, "transitional risk": 50397, "Taxonomy": 50289, "Carbon Disclosure Project": 50324, "risk assessment": 50332, "LBBW": 50416, "advise": 50273, "Intesa Sanpaolo": 50348, "global warming": 50295, "UNEP-FI": 50404, "Belgium": 50360, "renewable energy": 50277, "insurance": 50306, "adaptation": 50271, "Article 8": 50291, "prohibit": 50330, "Task Force on Climate Related Disclosures": 50308, "EU 2019/2089": 50327, "S.A": 50357, "SpA": 50356, "Banco Popolare": 50417, "financing": 50274, "environmental characteristics": 50338, "Rabobank": 50361, "significant harm": 50335, "Crédit Agricole": 50344, "CaixaBank": 50363, "carbon-neutral": 50391, "Societe Generale": 50409, " Landesbank Hessen-Thüringen": 50415, "A/S": 50381, "green bond": 50272, "operational risk": 50395, "plc": 50383, "ESG": 50392, "Banco de Sabadell": 50355, " advice": 50386, "initiative": 50340, "La Banque Postale": 50373, "clean energy": 50284, "due diligence": 50333, "Banco BPM": 50376, "PRI": 50406, "disclosure": 50299, "assessment": 50408, "recycling": 50313, "fossil fuels": 50298, "Raiffeisen Bank International": 50377, "Austria": 50372, "Handlesbanken": 50368, "mitigation": 50270, "UniCredit": 50345, "Carbon neutral": 50287, "bio energy ": 50281, "electricity": 50314, " transitional": 50398, "Finland": 50375, "loan": 50275, "credit risk": 50394, " regulatory risk": 50399, "UN Environmental Programme Finance Initiative": 50321, "Bank of Ireland": 50379, "operational": 50303, "carbon pricing": 50309, "UNEP": 50403, "exclusion": 50331, "2 Degrees Investing Initiative": 50325, "BPCE": 50346, "Deutsche Bank": 50347, "Erste": 50371, "Sociéte Générale": 50343, "SEB": 50410, "Netherlands": 50342, "BBVA": 50413, "TCFD": 50402, "Commerzbank": 50367, "SBTi": 50401, "controversial sector": 50329, "BNP Paribas": 50366, "benchmark": 50336, "climate transition": 50337, "adverse impact": 50267, "Sweden": 50350, "Banca Monte dei Paschi di Siena": 50378, "Article 9": 50290, "hydro power": 50280, "UN Environmental Programme": 50320, "Oy": 50382, " Paris aligned": 50389, "BayernLB": 50411, "geothermal": 50279, "Nordea": 50364, "physical risk": 50396, "negative impact": 50268, "ocean energy": 50282, "renewables": 50387, "Environmental, social and governance": 50297, "PRB": 50405, "CDP": 50407, "BMPS": 50419, "Skandinaviska Enskilda Banken": 50353, "KBC": 50369, "SDG": 50393, "procurement": 50334, "Swedbank": 50349, "regulatory": 50305, "Landesbank Hessen-Thüringen Girozentrale": 50362, "equator principles": 50317, "Sustainable Development Goal": 50300, "Award": 50302, "EU 20202/852": 50328, "advisory": 50385, "Bayerische Landesbank": 50354, "Danske Bank": 50365, "Banco Bilbao Vizcaya Argentina": 50358, "Belfius": 50359, "Scope 2 emission": 50293, "indicator": 50339, "Principles for Responsible Banking": 50322, "climate change": 50265, "Landesbank Baden Wüttemburg": 50370, "insurance risk": 50400, "net-zero": 50390, "EU 2019/2088": 50326, "sustainable": 50296, "bond": 50384, "N.V.": 50380, " MPS": 50420, "Nykredit": 50351, "emissions trading": 50310, "green energy": 50283, "Scope 1 emission": 50292, "Science Based Target initiative": 50307, "Scope 3 emission": 50294, "solar": 50278, "non-financial risk": 50316, "RE100": 50318, "emission": 50311, "transition": 50304, "Net Zero": 50286}

model/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/models/awesome-climate-lm-0917",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50421
+}

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e799d0489fe02a987cf47cf79b5c6ddb35704fb385032dd3c2aee5b06f25e2
+size 329005165

model/special_tokens_map.json

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

model/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/models/awesome-climate-lm-0917", "tokenizer_class": "RobertaTokenizer"}