Model Overview

The abvgkjhjh/fact_extractor_dev_1b is a 4 billion parameter Qwen3-based instruction-tuned model developed by abvgkjhjh. It was fine-tuned from unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit using the Unsloth library and Huggingface's TRL library, which facilitated a 2x faster training process.

Key Characteristics

• Architecture: Qwen3-based causal language model.
• Parameter Count: 4 billion parameters.
• Context Length: Supports a context length of 32768 tokens.
• Training Efficiency: Leverages Unsloth for significantly faster fine-tuning.
• License: Distributed under the Apache-2.0 license.

Intended Use

This model is specifically designed for fact extraction tasks, benefiting from its instruction-tuned nature and efficient training. Its Qwen3 architecture and substantial context window make it suitable for processing and extracting information from longer texts.