PrasannaPaithankar/qwen2.5-1.5b-sft-dare-resta
PrasannaPaithankar/qwen2.5-1.5b-sft-dare-resta is a 1.5 billion parameter language model based on the Qwen2.5 architecture, created by PrasannaPaithankar. This model is a merge of pre-trained language models using the Task Arithmetic method, specifically designed to modify the behavior of the base model. It integrates Qwen/Qwen2.5-1.5B-Instruct with a 'harmful_lora' component, suggesting a focus on adjusting or mitigating specific content generation characteristics.
Loading preview...
Model Overview
PrasannaPaithankar/qwen2.5-1.5b-sft-dare-resta is a 1.5 billion parameter language model derived from the Qwen2.5 architecture. It was created by PrasannaPaithankar using the mergekit tool, specifically employing the Task Arithmetic merge method.
Key Characteristics
- Base Model: The merge uses
PrasannaPaithankar/qwen2.5-1.5b-medical-sft-dareas its foundation. - Merged Components: It combines
Qwen/Qwen2.5-1.5B-Instructwith a component identified asoutputs/model_harmful_lora. - Merge Method: The Task Arithmetic method was applied, with
Qwen/Qwen2.5-1.5B-Instructhaving a weight of1.0andoutputs/model_harmful_lorahaving a negative weight of-1.0. This negative weighting in Task Arithmetic typically aims to subtract or reduce specific learned behaviors or characteristics introduced by the negatively weighted model.
Potential Use Cases
This model is likely intended for use cases where fine-grained control over content generation is desired, particularly in modifying or 'restoring' the behavior of a base model by subtracting specific learned traits. The inclusion of a 'harmful_lora' with a negative weight suggests an effort to mitigate or remove undesirable outputs, potentially related to safety or specific content biases, from the Qwen2.5-1.5B-Instruct base.