rakesh277/qwen05-resume-parser-v2

TEXT GENERATIONConcurrency Cost:1Model Size:0.5BQuant:BF16Ctx Length:32kPublished:Apr 26, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

rakesh277/qwen05-resume-parser-v2 is a 0.5 billion parameter Qwen2.5-based instruction-tuned model developed by rakesh277, fine-tuned from unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit. It was trained using Unsloth for accelerated fine-tuning and Huggingface's TRL library, featuring a 32768 token context length. This model is specifically optimized for resume parsing tasks, leveraging its compact size for efficient deployment.

Loading preview...

rakesh277/qwen05-resume-parser-v2 Overview

This model is a 0.5 billion parameter instruction-tuned variant of the Qwen2.5 architecture, developed by rakesh277. It was fine-tuned from the unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit base model, leveraging the Unsloth library for significantly faster training, alongside Huggingface's TRL library. This optimization allows for efficient fine-tuning, making it a practical choice for specific applications.

Key Capabilities

  • Efficient Fine-tuning: Utilizes Unsloth for 2x faster training compared to standard methods.
  • Compact Size: At 0.5 billion parameters, it offers a balance of performance and resource efficiency.
  • Extended Context: Supports a context length of 32768 tokens, suitable for processing longer documents.

Good for

  • Resume Parsing: Specifically designed and fine-tuned for extracting information from resumes.
  • Resource-Constrained Environments: Its small parameter count makes it suitable for deployment where computational resources are limited.
  • Rapid Prototyping: The accelerated training process facilitates quicker iteration and development cycles for specialized NLP tasks.