Tucano2-qwen-1.5B-Instruct

Model overview

Tucano2-qwen-1.5B-Instruct is published by Polygl0t as a Qwen3 text-generation model. The captured configuration identifies Qwen3ForCausalLM and Safetensors metadata reports 1,510,073,344 parameters. According to the model card, it instruction-tunes Tucano2-qwen-1.5B-Base for Portuguese with SFT and Anchored Preference Optimization.

Recorded capabilities

Use cases in the source record

• Portuguese research and development workflows, including retrieval-augmented generation, summarization, and structured output generation.
• Function-calling and tool-use experiments with Portuguese prompts, using the card's documented chat-template generation pattern.

Limitations and unknowns

• According to the model card, the model may hallucinate, repeat, or produce verbose output and is not an out-of-the-box solution for factual or nontoxic generation without risk assessment.
• According to the model card, benchmark tables compare Portuguese-task peers, but the captured table fragment lacks full headers; figures are publisher claims.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Polygl0t/Tucano2-qwen-1.5B-Instruct

Captured: Unknown. Processed: 2026-09-07T19:35:51.322388+00:00.

Tucano2-qwen-1.5B-Instruct Model Summary Tucano2-qwen-1.5B-Instruct is an instruction-tuned Portuguese language model on top of Tucano2-qwen-1.5B-Base . It has been trained using a combination of one round of supervised fine-tuning (SFT) and one round of Anchored Preference Optimization (APO). Despite its compact size, the model delivers strong performance across a wide range of Portuguese benchmarks and supports tasks such as retrieval-augmented generation , function calling and tool use , summarization , and structured output generation , among others. All datasets, source code, and training recipes used to develop the Tucano2 ser…