myfi/parser_model_ner_4.8
TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Apr 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
myfi/parser_model_ner_4.8 is a 4 billion parameter Qwen3-based instruction-tuned language model developed by myfi, fine-tuned for specific parsing tasks. This model leverages Unsloth and Huggingface's TRL library for accelerated training. It is designed for efficient performance in natural language processing applications requiring structured data extraction.
Loading preview...
Model Overview
myfi/parser_model_ner_4.8 is a 4 billion parameter language model developed by myfi, specifically fine-tuned for parsing tasks. It is based on the Qwen3 architecture and was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.
Key Capabilities
- Efficient Fine-tuning: Benefits from Unsloth's optimization for faster training.
- Qwen3 Architecture: Leverages the robust base of the Qwen3 model family.
- Specialized for Parsing: Designed to excel in tasks involving structured data extraction from text.
Good For
- Applications requiring efficient and accurate parsing of natural language.
- Developers looking for a Qwen3-based model optimized for specific data extraction challenges.
- Use cases where accelerated training methods are beneficial for model development.