yilmazzey/qwen2_5_1_5b-abstract-finetuned-ep1-b4

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Apr 5, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The yilmazzey/qwen2_5_1_5b-abstract-finetuned-ep1-b4 is a 1.5 billion parameter Qwen2.5 model developed by yilmazzey, fine-tuned from unsloth/qwen2.5-1.5b. This model was trained using Unsloth for accelerated performance, offering a compact yet capable language model. It is designed for general language tasks, leveraging its Qwen2.5 architecture and efficient training methodology.

Loading preview...

Model Overview

The yilmazzey/qwen2_5_1_5b-abstract-finetuned-ep1-b4 is a 1.5 billion parameter language model based on the Qwen2.5 architecture. Developed by yilmazzey, this model is a fine-tuned version of unsloth/qwen2.5-1.5b and was trained with Unsloth, which facilitated a 2x faster training process.

Key Characteristics

  • Architecture: Qwen2.5 base model.
  • Parameters: 1.5 billion, offering a balance between performance and computational efficiency.
  • Training Efficiency: Utilizes Unsloth for optimized and accelerated fine-tuning.
  • Context Length: Supports a context window of 32768 tokens.
  • License: Distributed under the Apache-2.0 license.

Potential Use Cases

This model is suitable for applications requiring a compact yet capable language model, particularly where efficient inference and deployment are important. Its Qwen2.5 foundation suggests general language understanding and generation capabilities, making it a candidate for tasks such as:

  • Text summarization.
  • Content generation.
  • Chatbot development.
  • Abstractive tasks, given its fine-tuning origin.