Assaoka/Tucano2-qwen-0.5b-Merge-Phrasebank

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 14, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Assaoka/Tucano2-qwen-0.5b-Merge-Phrasebank is an 0.8 billion parameter Qwen-based model developed by Assaoka, specialized in Portuguese sentiment analysis. It was created using a Knowledge Accumulation (Prior) strategy, merging multiple expert models and then fine-tuned on a Portuguese Financial Phrasebank dataset. This model excels at classifying sentiment (positive, negative, neutral) in financial texts in Portuguese, demonstrating significant performance improvements over its baseline.

Loading preview...

Model Overview

Assaoka/Tucano2-qwen-0.5b-Merge-Phrasebank is an 0.8 billion parameter model developed by Assaoka, specifically designed for sentiment analysis in Portuguese. It leverages a Knowledge Accumulation (Prior) strategy, where it was initially merged from several specialized models including Assaoka/Tucano2-qwen-0.5B-ReLiSA, Assaoka/Tucano2-qwen-0.5B-Brighter, Assaoka/Tucano2-qwen-0.5B-FinBERT, and Assaoka/Tucano2-qwen-0.5B-GoEmotions. Following this merge, the model underwent sequential fine-tuning on the mateuspicanco/financial-phrase-bank-portuguese-translation dataset.

Key Capabilities

  • Specialized Sentiment Analysis: Expertly classifies sentiment (positive, negative, neutral) within financial texts in Portuguese.
  • Enhanced Performance: Demonstrates substantial improvements across various sentiment analysis benchmarks compared to its Polygl0t/Tucano2-qwen-0.5B-Instruct baseline, particularly on the FINANCIAL-PHRASEBANK dataset (85.32% Macro F1 vs. 38.13% baseline).
  • Structured Output: Designed to respond with structured JSON outputs for sentiment classification, facilitating integration into applications.
  • Portuguese Language Focus: Optimized for the nuances of Brazilian Portuguese (PT-BR).

Ideal Use Cases

This model is particularly well-suited for:

  • Financial Sentiment Analysis: Analyzing news, reports, or social media related to finance in Portuguese to gauge market sentiment.
  • Automated Content Moderation: Identifying sentiment in user-generated content or customer feedback in Portuguese.
  • Academic Research: Serving as a robust tool for studies involving sentiment analysis in Portuguese, especially within financial contexts.

Finetunes
1 models