Upload folder using huggingface_hub

README.md

@@ -0,0 +1,106 @@
+---
+license: mit
+tags:
+- sentiment analysis
+- financial sentiment analysis
+- bert
+- text-classification
+- finance
+- finbert
+- financial
+---
+# Trading Hero Financial Sentiment Analysis
+
+Model Description: This model is a fine-tuned version of [FinBERT](https://huggingface.co/yiyanghkust/finbert-pretrain), a BERT model pre-trained on financial texts. The fine-tuning process was conducted to adapt the model to specific financial NLP tasks, enhancing its performance on domain-specific applications for sentiment analysis.
+
+## Model Use
+
+Primary Users: Financial analysts, NLP researchers, and developers working on financial data.
+
+## Training Data
+
+Training Dataset: The model was fine-tuned on a custom dataset of financial communication texts. The dataset was split into training, validation, and test sets as follows:
+
+Training Set: 10,918,272 tokens
+
+Validation Set: 1,213,184 tokens
+
+Test Set: 1,347,968 tokens
+
+Pre-training Dataset: FinBERT was pre-trained on a large financial corpus totaling 4.9 billion tokens, including:
+
+Corporate Reports (10-K & 10-Q): 2.5 billion tokens
+
+Earnings Call Transcripts: 1.3 billion tokens
+
+Analyst Reports: 1.1 billion tokens
+
+## Evaluation
+
+* Test Accuracy = 0.908469
+* Test Precision = 0.927788
+* Test Recall = 0.908469
+* Test F1 = 0.913267
+* **Labels**: 0 -> Neutral; 1 -> Positive; 2 -> Negative
+
+
+## Usage
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+tokenizer = AutoTokenizer.from_pretrained("fuchenru/Trading-Hero-LLM")
+model = AutoModelForSequenceClassification.from_pretrained("fuchenru/Trading-Hero-LLM")
+nlp = pipeline("text-classification", model=model, tokenizer=tokenizer)
+# Preprocess the input text
+def preprocess(text, tokenizer, max_length=128):
+    inputs = tokenizer(text, truncation=True, padding='max_length', max_length=max_length, return_tensors='pt')
+    return inputs
+
+# Function to perform prediction
+def predict_sentiment(input_text):
+    # Tokenize the input text
+    inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True)
+
+    # Perform inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    # Get predicted label
+    predicted_label = torch.argmax(outputs.logits, dim=1).item()
+
+    # Map the predicted label to the original labels
+    label_map = {0: 'neutral', 1: 'positive', 2: 'negative'}
+    predicted_sentiment = label_map[predicted_label]
+
+    return predicted_sentiment
+
+stock_news = [
+    "Market analysts predict a stable outlook for the coming weeks.",
+    "The market remained relatively flat today, with minimal movement in stock prices.",
+    "Investor sentiment improved following news of a potential trade deal.",
+.......
+]
+
+
+for i in stock_news:
+    predicted_sentiment = predict_sentiment(i)
+    print("Predicted Sentiment:", predicted_sentiment)
+```
+```
+Predicted Sentiment: neutral
+Predicted Sentiment: neutral
+Predicted Sentiment: positive
+```
+
+## Citation
+
+```
+@misc{yang2020finbert,
+    title={FinBERT: A Pretrained Language Model for Financial Communications},
+    author={Yi Yang and Mark Christopher Siy UY and Allen Huang},
+    year={2020},
+    eprint={2006.08097},
+    archivePrefix={arXiv},
+    }
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "model_df_7",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30873
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5411019d7b22b5376249eb3d50ed59772f0b93419849580e16e7d060935f69a7
+size 439039996

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}