Release model versions in onnx

.gitignore

@@ -19,7 +19,6 @@ sentiment_env/
 gguf_env/
 dataset/
 export_model_script/
-financial_sentiment_analyzer_v1/
 # =========================================
 # Jupyter Notebook
 # =========================================

README.md

@@ -89,6 +89,191 @@ model = AutoModelForSequenceClassification.from_pretrained(
 )
 ```
 
+# 🚀 Using the ONNX Model
+
+This repository contains an optimized **ONNX Runtime** version of the Financial Sentiment Analyzer for fast CPU and GPU inference.
+
+## Installation
+
+```bash
+pip install onnxruntime optimum transformers
+```
+
+For NVIDIA GPU inference:
+
+```bash
+pip install onnxruntime-gpu optimum transformers
+```
+
+---
+
+## Download the Model
+
+Clone the repository:
+
+```bash
+git clone https://huggingface.co/sbasu2512/financial_sentiment_model
+```
+
+or download the model directly from Hugging Face:
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer
+
+MODEL_NAME = "sbasu2512/financial_sentiment_analyzer_v2"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = ORTModelForSequenceClassification.from_pretrained(MODEL_NAME)
+```
+
+---
+
+# Local Usage
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer
+
+MODEL_PATH = "./financial_sentiment_analyzer_v2"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = ORTModelForSequenceClassification.from_pretrained(MODEL_PATH)
+```
+
+---
+
+# Basic Inference
+
+```python
+import torch
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer
+
+MODEL_PATH = "./financial_sentiment_analyzer_v2"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = ORTModelForSequenceClassification.from_pretrained(MODEL_PATH)
+
+text = """
+Reliance Industries reported record quarterly profits,
+beating analyst expectations.
+"""
+
+inputs = tokenizer(
+    text,
+    return_tensors="pt",
+    truncation=True,
+    max_length=512,
+)
+
+outputs = model(**inputs)
+
+prediction = torch.argmax(outputs.logits, dim=1).item()
+
+labels = {
+    0: "Negative",
+    1: "Neutral",
+    2: "Positive",
+}
+
+print(labels[prediction])
+```
+
+Example output:
+
+```
+Positive
+```
+
+---
+
+# Confidence Scores
+
+```python
+import torch
+
+probabilities = torch.softmax(outputs.logits, dim=1)[0]
+
+labels = ["Negative", "Neutral", "Positive"]
+
+for label, probability in zip(labels, probabilities):
+    print(f"{label}: {probability:.4f}")
+```
+
+Example output:
+
+```
+Negative : 0.0124
+Neutral  : 0.0836
+Positive : 0.9040
+```
+
+---
+
+# Predict Multiple Headlines
+
+```python
+headlines = [
+    "Tata Motors reports record EV sales.",
+    "Markets remained largely unchanged today.",
+    "Company files for bankruptcy protection.",
+]
+
+inputs = tokenizer(
+    headlines,
+    padding=True,
+    truncation=True,
+    max_length=512,
+    return_tensors="pt",
+)
+
+outputs = model(**inputs)
+
+predictions = torch.argmax(outputs.logits, dim=1)
+
+labels = ["Negative", "Neutral", "Positive"]
+
+for headline, pred in zip(headlines, predictions):
+    print(f"{headline}\n→ {labels[pred.item()]}\n")
+```
+
+Example output:
+
+```
+Tata Motors reports record EV sales.
+→ Positive
+
+Markets remained largely unchanged today.
+→ Neutral
+
+Company files for bankruptcy protection.
+→ Negative
+```
+
+---
+
+# Output Labels
+
+| ID | Sentiment |
+|---:|------------|
+| 0 | Negative |
+| 1 | Neutral |
+| 2 | Positive |
+
+---
+
+# Performance
+
+The ONNX version provides significantly faster inference than the original PyTorch model while maintaining identical predictions. It is suitable for:
+
+- Real-time news sentiment analysis
+- Trading pipelines
+- Financial research
+- Batch inference
+- REST APIs
+- Production deployment
+
 ## 🧩 Intended Use
 
 - Real-time sentiment analysis for Indian and global stock market news.

model_exports/financial_sentiment_analyzer_v1.0.0/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 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",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model_exports/financial_sentiment_analyzer_v1.0.0/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba99fd8667d0fb95e297a4a41e37477bd073aaa27c546492e233868e9d0245a6
+size 438148594

model_exports/financial_sentiment_analyzer_v1.0.0/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
+  }
+}

model_exports/financial_sentiment_analyzer_v1.0.0/tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

model_exports/financial_sentiment_analyzer_v2.0.0/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 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",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model_exports/financial_sentiment_analyzer_v2.0.0/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5201f5f5d769bc38a2b3f2f430e584458361701a245ea1a499bc6a10a7d197c
+size 438148594

model_exports/financial_sentiment_analyzer_v2.0.0/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
+  }
+}

model_exports/financial_sentiment_analyzer_v2.0.0/tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}