Model Overview

The myfi/parser_model_ner_3.98 is a 4 billion parameter language model developed by myfi. It is based on the Qwen3 architecture and has been instruction-tuned for specific applications. This model was finetuned from unsloth/Qwen3-4B-Instruct-2507.

Key Characteristics

• Architecture: Qwen3-based, a robust foundation for language understanding.
• Parameter Count: 4 billion parameters, offering a balance between performance and computational efficiency.
• Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
• Context Length: Supports a context window of 32768 tokens, allowing for processing of longer inputs.

Potential Use Cases

This model is particularly suited for tasks requiring specialized parsing capabilities, given its instruction-tuned nature and efficient training methodology. Its Qwen3 foundation makes it adaptable for various natural language processing applications where a focused, efficient model is beneficial.