bunnycore/Qwen-2.5-3b-Evol-CoT-V3

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Qwen/Qwen2.5-3B + bunnycore/qwen-2.5-3b-lora_model as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Qwen-2.5-3b-Evol-CoT + bunnycore/qwen-2.5-3b-lora_model
• bunnycore/Qwen-2.5-3b-RP
• bunnycore/Qwen-2.5-3b-Evol-CoT-v2 + bunnycore/Qwen-2.5-3b-Mix-Data-lora

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Qwen-2.5-3b-Evol-CoT+bunnycore/qwen-2.5-3b-lora_model
  - model: bunnycore/Qwen-2.5-3b-RP
  - model: bunnycore/Qwen-2.5-3b-Evol-CoT-v2+bunnycore/Qwen-2.5-3b-Mix-Data-lora
merge_method: model_stock
base_model: Qwen/Qwen2.5-3B+bunnycore/qwen-2.5-3b-lora_model
parameters:
  normalize: false
  int8_mask: true
dtype: float16