| base_model: Qwen/Qwen3-4B | |
| tags: | |
| - llama-factory | |
| - qwen3 | |
| - fine-tuned | |
| - merged | |
| license: apache-2.0 | |
| language: | |
| - en | |
| - zh | |
| datasets: | |
| - tags_and_summary | |
| pipeline_tag: text-generation | |
| model_type: qwen2 | |
| # model_backup | |
| This is a **merged fine-tuned model** based on [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B). The LoRA adapters have been merged into the base model, creating a standalone fine-tuned model. | |
| ## Model Description | |
| This language model has been fine-tuned using LLaMA-Factory and then merged with the base model. It specializes in email search and related tasks. | |
| ## Model Details | |
| - **Base Model**: Qwen/Qwen3-4B | |
| - **Model Size**: ~4B parameters | |
| - **Architecture**: Qwen3 | |
| - **Training Method**: LoRA fine-tuning + model merging | |
| - **Dataset**: tags_and_summary | |
| - **Use Case**: Email search and analysis | |