daraai-dev/Qwen2.5-0.5B-MAIMD-SPECTRUM-123HPI

TEXT GENERATIONConcurrency Cost:1Model Size:0.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 2, 2026Architecture:Transformer Cold

daraai-dev/Qwen2.5-0.5B-MAIMD-SPECTRUM-123HPI is a 0.5 billion parameter language model, fine-tuned from Qwen/Qwen2.5-0.5B-Instruct using the TRL framework. This model is specifically trained with Supervised Fine-Tuning (SFT) to enhance its instruction-following capabilities. It is designed for general text generation tasks where a compact yet capable instruction-tuned model is required, leveraging its 32K context length for processing longer prompts.

Loading preview...

Model Overview

daraai-dev/Qwen2.5-0.5B-MAIMD-SPECTRUM-123HPI is a compact 0.5 billion parameter language model, built upon the Qwen2.5-0.5B-Instruct architecture. It has been further fine-tuned using the TRL (Transformers Reinforcement Learning) library to improve its performance in instruction-following tasks.

Key Characteristics

  • Base Model: Fine-tuned from Qwen/Qwen2.5-0.5B-Instruct.
  • Training Method: Utilizes Supervised Fine-Tuning (SFT) for enhanced instruction adherence.
  • Context Length: Supports a context window of 32,768 tokens, allowing for processing of substantial input prompts.
  • Frameworks: Developed using TRL (version 1.5.1), Transformers (version 5.0.0), Pytorch (version 2.11.0+cu128), Datasets (version 4.8.5), and Tokenizers (version 0.22.2).

Use Cases

This model is suitable for applications requiring a small, efficient, and instruction-tuned language model. Its fine-tuning process makes it particularly effective for:

  • General text generation based on user instructions.
  • Quick prototyping and deployment in resource-constrained environments.
  • Tasks benefiting from a 32K context window for understanding longer queries or documents.