---

license: apache-2.0

---

!1783090905

(v3 preview check out there and report me any bugs: https://huggingface.co/14ai/Polando-v3-1.7b-THINKING-PREVIEW)

Polando v2-1.5B

Fine-tuned on Polish conversational datasets (such as Emplocity/Owca), this updated release delivers better Polish language and better logic than Polando-v1-1b.

---

Key Improvements

• Better Polish than Polando-v1-1b.
• The model finally can do greetings like hello or something.
• Better logic than Polando-v1-1b.
• It is a fine-tuned Qwen, so it speaks its name is Qwen.

---

Technical Specifications

| Parameter | Specification |

| :--- | :--- |

| Base Architecture | Qwen2.5-1.5B-Instruct |

| Format | Merged FP16 (Full Precision) |

| File Size | ~3 GB (model.safetensors) |

| Dependencies | Standard transformers library (Native execution; no PEFT/LoRA required) |

---

Recommended Generation Parameters

generation_config = {
    "max_new_tokens": 512,        # Adjust based on your needs
    "min_new_tokens": 1,
    "do_sample": True,
    "temperature": 0.2,           # Recommended range: 0.1 - 0.3 for precise responses
    "top_p": 0.85,
    "repetition_penalty": 1.15
}