aashish093/qwen2.5-3b-scheme-extract

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 19, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The aashish093/qwen2.5-3b-scheme-extract is a 3.1 billion parameter Qwen2.5-based causal language model, finetuned by aashish093. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is optimized for specific extraction tasks, leveraging its efficient finetuning process.

Loading preview...

Overview

The aashish093/qwen2.5-3b-scheme-extract is a 3.1 billion parameter language model, finetuned by aashish093. It is based on the Qwen2.5 architecture and was specifically trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process compared to standard methods.

Key Characteristics

  • Base Model: Finetuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit.
  • Efficient Training: Utilizes Unsloth for accelerated finetuning.
  • Parameter Count: Features 3.1 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a context window of 32768 tokens.

Potential Use Cases

This model is suitable for applications requiring a compact yet capable language model, especially where efficient finetuning is a priority. Its specific finetuning suggests it is well-suited for tasks involving data extraction or schema-based information retrieval, leveraging the Qwen2.5 architecture's strengths.