cutelemonlili/Qwen_7B_RL_dsr4k_last_8

output_7B_last_8

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

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

• UWNSL/Qwen2.5-7B-deepscaler_4k_step_32
• UWNSL/Qwen2.5-7B-deepscaler_4k_step_64
• UWNSL/Qwen2.5-7B-deepscaler_4k_step_192
• UWNSL/Qwen2.5-7B-deepscaler_4k_step_128
• UWNSL/Qwen2.5-7B-deepscaler_4k_step_160
• UWNSL/Qwen2.5-7B-deepscaler_4k_step_96
• UWNSL/Qwen2.5-7B-deepscaler_4k_step_256
• UWNSL/Qwen2.5-7B-deepscaler_4k_step_224

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_224
    parameters:
      weight: 0.125
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_256
    parameters:
      weight: 0.125
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_192
    parameters:
      weight: 0.125
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_160
    parameters:
      weight: 0.125
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_128
    parameters:
      weight: 0.125
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_96
    parameters:
      weight: 0.125
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_64
    parameters:
      weight: 0.125
  - model: UWNSL/Qwen2.5-7B-deepscaler_4k_step_32
    parameters:
      weight: 0.125
merge_method: linear
dtype: float16