initial commit

README.md

@@ -0,0 +1,58 @@
+---
+language: en
+widget:
+- text: "I am going to buy 100 shares of cake tomorrow"
+---
+
+# roberta-ticker: model was fine-tuned from Roberta to detect financial tickers
+
+## Introduction
+
+This is a model specifically designed to identify tickers in text.
+Model was trained on transformed dataset from following Kaggle dataset:
+https://www.kaggle.com/omermetinn/tweets-about-the-top-companies-from-2015-to-2020
+
+
+
+## How to use roberta-ticker with HuggingFace
+
+##### Load roberta-ticker and its sub-word tokenizer :
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+tokenizer = AutoTokenizer.from_pretrained("Jean-Baptiste/roberta-ticker")
+model = AutoModelForTokenClassification.from_pretrained("Jean-Baptiste/roberta-ticker")
+
+
+##### Process text sample 
+
+from transformers import pipeline
+
+nlp = pipeline('ner', model=model, tokenizer=tokenizer, grouped_entities=True, ignore_labels='O')
+
+nlp("I am going to buy 100 shares of cake tomorrow")
+[{'entity_group': 'TICKER',
+  'score': 0.9612462520599365,
+  'word': ' cake',
+  'start': 32,
+  'end': 36}]
+  
+nlp("I am going to eat cake tomorrow")
+[]
+ 
+
+
+```
+
+
+## Model performances
+
+
+```
+precision: 0.8905576596578294
+recall: 0.900554675118859
+f1: 0.8955282684352223
+
+ ```
+

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "../models_data/models/roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "TICKER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "TICKER": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cbfa584183c16692abfff352ab3997b9cc868e30cc74c38919f67002f252bae
+size 496315695

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}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "../models_data/models/roberta-base", "special_tokens_map_file": "../models_data/models/roberta-base\\special_tokens_map.json"}