cnmoro/Qwen2.5-0.5B-Portuguese-v1
The cnmoro/Qwen2.5-0.5B-Portuguese-v1 is a 0.5 billion parameter Qwen2.5-Instruct model, fine-tuned by cnmoro for enhanced proficiency in the Portuguese language. This model is optimized for various Portuguese natural language processing tasks, including text generation and understanding. It demonstrates specific performance metrics across several Portuguese benchmarks, making it suitable for applications requiring strong Portuguese language capabilities.
Loading preview...
Model Overview
The cnmoro/Qwen2.5-0.5B-Portuguese-v1 is a 0.5 billion parameter language model based on the Qwen2.5-0.5B-Instruct architecture. It has been specifically fine-tuned by cnmoro to achieve high proficiency and increased intelligence in the Portuguese language. The model supports a context length of 32768 tokens.
Key Capabilities
- Portuguese Language Optimization: Extensive fine-tuning on Portuguese datasets such as
adalbertojunior/openHermes_portuguese,cnmoro/smoltalk-555k-ptbr, andcnmoro/RagMixPTBR-Legal-Alpaca-2Mfor superior performance in Portuguese. - Multilingual Support: While optimized for Portuguese, the base model supports a wide range of languages including Chinese, English, French, Spanish, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.
- Benchmark Performance: Evaluated on the Open Portuguese LLM Leaderboard, achieving an average score of 50.74. Notable scores include 86.30 on Assin2 RTE and 65.33 on FaQuAD NLI.
Good for
- Applications requiring robust Portuguese text generation and understanding.
- Tasks involving Portuguese-specific benchmarks like ENEM Challenge, BLUEX, and OAB Exams.
- Use cases where a smaller, efficient model with strong Portuguese capabilities is preferred.