Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+language:
+  - en
+  - zh
+  - ja
+  - de
+  - fr
+  - es
+tags:
+  - finance
+  - sentiment-analysis
+  - multilingual
+  - xlm-roberta
+datasets:
+  - Kenpache/multilingual-financial-sentiment
+metrics:
+  - accuracy
+  - f1
+pipeline_tag: text-classification
+model-index:
+  - name: FLAME
+    results:
+      - task:
+          type: text-classification
+          name: Financial Sentiment Analysis
+        metrics:
+          - name: Accuracy
+            type: accuracy
+            value: 0.8103
+          - name: F1 (weighted)
+            type: f1
+            value: 0.8102
+---
+
+# FLAME - Financial Language Analysis for Multilingual Economics
+
+**One model. Six languages. Real financial sentiment.**
+
+FLAME classifies financial text as **Negative**, **Neutral**, or **Positive** across English, Chinese, Japanese, German, French, and Spanish.
+
+Built on XLM-RoBERTa-base, domain-adapted on 35K+ financial texts, fine-tuned on ~39K multilingual financial news samples.
+
+## Quick Start
+
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model="Kenpache/flame")
+
+classifier("Revenue surged 40% year-over-year, beating analyst expectations.")
+# [{'label': 'positive', 'score': 0.96}]
+
+classifier("La empresa reportó pérdidas significativas este trimestre.")
+# [{'label': 'negative', 'score': 0.93}]
+```
+
+## Results
+
+| Metric | Score |
+|---|---|
+| Accuracy | **0.8103** |
+| F1 (weighted) | **0.8102** |
+| Precision | **0.8111** |
+| Recall | **0.8103** |
+
+| Class | Precision | Recall | F1 |
+|---|---|---|---|
+| Negative | 0.78 | 0.83 | 0.81 |
+| Neutral | 0.83 | 0.79 | 0.81 |
+| Positive | 0.80 | 0.82 | 0.81 |
+
+## Languages
+
+EN | ZH | JA | DE | FR | ES
+
+## Training
+
+XLM-RoBERTa-base + Task-Adaptive Pre-Training (MLM) + fine-tuning with label smoothing, cosine LR schedule, and SWA checkpoint averaging.
+
+## Dataset
+
+[Kenpache/multilingual-financial-sentiment](https://huggingface.co/datasets/Kenpache/multilingual-financial-sentiment) -- ~39K samples from CNBC, Yahoo Finance, Reuters, Nikkei, Sina Finance, and 80+ other financial news sources.
+
+## License
+
+Apache 2.0