Kalash2107/deepseekr1-resume-parser-v5
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Apr 29, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The Kalash2107/deepseekr1-resume-parser-v5 is a 1.5 billion parameter Qwen2 model, developed by Kalash2107, with a 32768 token context length. This model was fine-tuned using Unsloth and Huggingface's TRL library, resulting in 2x faster training. It is specifically designed for resume parsing tasks, leveraging its efficient training and Qwen2 architecture for specialized information extraction.
Loading preview...
Model Overview
Kalash2107/deepseekr1-resume-parser-v5 is a specialized 1.5 billion parameter Qwen2 model, developed by Kalash2107. It is built upon the unsloth/deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit base model and features a substantial context length of 32768 tokens.
Key Characteristics
- Efficient Training: This model was fine-tuned using the Unsloth library, which enabled 2x faster training compared to standard methods, alongside Huggingface's TRL library.
- Specialized Fine-tuning: The model is specifically designed and fine-tuned for resume parsing, indicating its optimization for extracting structured information from resumes.
- Qwen2 Architecture: Leverages the Qwen2 architecture, known for its strong performance in various language understanding tasks.
Use Cases
- Resume Parsing: Ideal for applications requiring the extraction of key information from resumes, such as applicant tracking systems, recruitment platforms, or HR automation tools.
- Information Extraction: Suitable for tasks involving structured data extraction from semi-structured text documents, particularly those similar in format to resumes.