Qwen3-1.7b-gsm8k-leetcode-task-arithmetic

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/Qwen3-1.7B as a base.

Models Merged

The following models were included in the merge:

/content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/qwen3-1.7b-gsm8k-merged
/content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/qwen3-1.7b-leetcode-merged

Configuration

The following YAML configuration was used to produce this model:

# merge_task_arithmetic.yml
models:
  - model: /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/qwen3-1.7b-gsm8k-merged
    parameters:
      weight: 0.65  # Giữ nguyên model chính
  - model: /content/drive/MyDrive/Khoá_luận_tốt_nghiệp/Model/qwen3-1.7b-leetcode-merged
    parameters:
      weight: 0.35  # Scale task vector từ Pyxidis
merge_method: task_arithmetic
base_model: /content/Qwen3-1.7B  # Pre-trained base (trước fine-tune)
dtype: bfloat16
tokenizer_source: union
parameters:
  normalize: true
  # Áp dụng weight khác nhau theo layer
  int8_mask: false

Downloads last month: 249

Safetensors

Model size

2B params

Tensor type

BF16

Paper for quangdung/Qwen3-1.7b-gsm8k-leetcode-task-arithmetic

Editing Models with Task Arithmetic

Paper • 2212.04089 • Published Dec 8, 2022 • 7