divaspoudel/iol-ai-challenge

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 14, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The divaspoudel/iol-ai-challenge model is an instruction-tuned 7.61 billion parameter causal language model from the Qwen2.5 series, developed by Qwen. It features a transformer architecture with RoPE, SwiGLU, RMSNorm, and Attention QKV bias, supporting a context length of up to 128K tokens and generating up to 8K tokens. This model significantly improves capabilities in coding, mathematics, instruction following, and generating structured outputs like JSON, while also offering multilingual support for over 29 languages.

Loading preview...

Overview

This model, divaspoudel/iol-ai-challenge, is an instruction-tuned variant of the Qwen2.5-7B model, developed by Qwen. It is a 7.61 billion parameter causal language model built on a transformer architecture incorporating RoPE, SwiGLU, RMSNorm, and Attention QKV bias. A key feature is its long-context support, capable of handling up to 128K tokens for input and generating up to 8K tokens, with the ability to extend context further using YaRN for inputs exceeding 32,768 tokens.

Key Capabilities

  • Enhanced Knowledge & Reasoning: Significantly improved capabilities in coding and mathematics, leveraging specialized expert models.
  • Instruction Following: Demonstrates substantial improvements in adhering to instructions and generating structured outputs, particularly JSON.
  • Long Text Generation: Excels at generating long texts, supporting outputs over 8K tokens.
  • Multilingual Support: Provides robust support for over 29 languages, including major global languages like Chinese, English, French, Spanish, and Japanese.
  • System Prompt Resilience: More resilient to diverse system prompts, enhancing role-play and condition-setting for chatbots.

When to Use This Model

This model is particularly well-suited for applications requiring:

  • Advanced Code Generation: Its strong coding capabilities make it ideal for developer tools and programming assistance.
  • Mathematical Problem Solving: Effective for tasks involving complex mathematical reasoning.
  • Structured Data Processing: Excellent for understanding structured data (e.g., tables) and generating structured outputs like JSON.
  • Multilingual Applications: Its broad language support makes it suitable for global applications and content generation in multiple languages.
  • Long-form Content Creation: Capable of generating extensive texts and handling large input contexts, beneficial for summarization or detailed content generation.

Finetunes
1 models