LOKA69/qwen2.5-1.5b-instruct-mirror

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 12, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The LOKA69/qwen2.5-1.5b-instruct-mirror is an instruction-tuned causal language model from the Qwen2.5 series by Qwen, featuring 1.54 billion parameters and a 32,768 token context length. This model significantly improves upon Qwen2 with enhanced capabilities in coding, mathematics, instruction following, and generating long texts. It also excels at understanding structured data and producing structured outputs like JSON, making it suitable for diverse chatbot applications and multilingual tasks across 29 languages.

Loading preview...

Qwen2.5-1.5B-Instruct Overview

This model is an instruction-tuned variant of the Qwen2.5 series, developed by Qwen. It is a causal language model with 1.54 billion parameters and supports a context length of 32,768 tokens, with generation capabilities up to 8,192 tokens. The architecture is based on transformers, incorporating RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings.

Key Capabilities & Improvements

  • Enhanced Knowledge & Reasoning: Significantly improved performance in coding and mathematics, leveraging specialized expert models.
  • Instruction Following: Demonstrates substantial improvements in adhering to instructions and generating coherent long texts (over 8K tokens).
  • Structured Data Handling: Excels at understanding structured data, such as tables, and generating structured outputs, particularly JSON.
  • Robustness: More resilient to diverse system prompts, which enhances role-play implementation and condition-setting for chatbots.
  • Multilingual Support: Provides comprehensive support for over 29 languages, including major global languages like Chinese, English, French, Spanish, German, and Japanese.

When to Use This Model

This model is particularly well-suited for applications requiring:

  • Code Generation & Mathematical Problem Solving: Due to its specialized training in these domains.
  • Complex Instruction Following: For tasks where precise adherence to prompts is critical.
  • Structured Output Generation: Ideal for scenarios needing JSON or other structured data formats.
  • Multilingual Chatbots & Content Generation: Its broad language support makes it versatile for global applications.
  • Long-form Content Creation: Capable of generating extended texts while maintaining coherence.

Finetunes
1 models