Qwen2.5-1.5b-leetcode-math-task-arithmetic-freeze-embed

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/Qwen2.5-1.5B-Instruc-base as a base.

Models Merged

The following models were included in the merge:

• /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/Qwen2.5-1.5B-Thinking-v1.1
• /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/Qwen2.5-1.5B-Instruct_LeetCodeDataset

Configuration

The following YAML configuration was used to produce this model:

# merge_config_embed_freeze.yaml

merge_method: task_arithmetic
base_model: /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/Qwen2.5-1.5B-Instruc-base

parameters:
  # Default: không merge gì (weight = 0)
  weight: 0.0

models:
  - model: /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/Qwen2.5-1.5B-Thinking-v1.1
    parameters:
      weight:
        - filter: model.layers
          value: 0.10
        - filter: model.embed_tokens
          value: 0.0
        - filter: lm_head
          value: 0.0

  - model: /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/Qwen2.5-1.5B-Instruct_LeetCodeDataset
    parameters:
      weight:
        - filter: model.layers
          value: 0.10
        - filter: model.embed_tokens
          value: 0.0
        - filter: lm_head
          value: 0.0

dtype: bfloat16