Upload om model files

README.md

@@ -0,0 +1,78 @@
+---
+language: en
+license: apache-2.0
+tags:
+  - financial-nlp
+  - sentiment-analysis
+  - distilroberta
+  - active-learning
+  - transformers
+datasets:
+  - financial_phrasebank
+metrics:
+  - accuracy
+  - f1
+model-index:
+  - name: hitenkatariya/FinStream
+    results:
+      - task:
+          type: text-classification
+        dataset:
+          name: Financial PhraseBank
+          type: financial_phrasebank
+        metrics:
+          - type: accuracy
+            value: 0.8680
+---
+
+# 📈 FinStream: Financial Sentiment Analysis
+
+> Fine-tuned `distilroberta-base` for 3-class financial sentiment classification.
+> Part of the **FinStream** active learning pipeline.
+
+## Model Description
+
+FinStream is a **DistilRoBERTa-base** model fine-tuned on the Financial PhraseBank dataset
+(`sentences_allagree` subset) to classify financial news into three sentiment classes:
+
+| Label | ID | Meaning |
+|-------|----|---------|
+| 🐻 bearish | 0 | Negative market outlook |
+| 😐 neutral | 1 | No strong directional signal |
+| 🐂 bullish | 2 | Positive market outlook |
+
+## Performance
+
+| Metric | Score |
+|--------|-------|
+| Test Accuracy | 0.8680 |
+| Training Set | Financial PhraseBank (all_agree) |
+
+## Usage
+
+```python
+from transformers import pipeline
+
+classifier = pipeline(
+    'text-classification',
+    model='hitenkatariya/FinStream',
+)
+
+result = classifier("Federal Reserve signals interest rate cuts.")
+print(result)  # [{'label': 'bullish', 'score': 0.94}]
+```
+
+## Training
+
+- **Base Model:** `distilroberta-base`
+- **Dataset:** Financial PhraseBank (`sentences_allagree`)
+- **Framework:** Hugging Face Transformers + Trainer API
+- **Optimizer:** AdamW with linear warmup
+- **Mixed Precision:** FP16 (on GPU)
+- **Early Stopping:** Patience = 3 (monitoring eval_f1)
+
+## Authors
+
+**Hiten Katariya** | **OM Choksi**
+
+Built as part of the FinStream Active Learning Pipeline — a portfolio-grade financial NLP project.

config.json

@@ -0,0 +1,39 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "bearish",
+    "1": "neutral",
+    "2": "bullish"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "bearish": 0,
+    "bullish": 2,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

eval_metrics.json

@@ -0,0 +1,9 @@
+{
+  "test_accuracy": 0.8679504814305364,
+  "timestamp": "2026-05-26T07:10:52.344448",
+  "base_model": "distilroberta-base",
+  "dataset": "financial_phrasebank/sentences_allagree",
+  "num_labels": 3,
+  "max_length": 128,
+  "seed": 42
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31667f355505bb2f76dc4e966015947974bcabf97737445697ec75915e12ce42
+size 328495340

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}