thiflaf's picture
Upload folder using huggingface_hub
5ce4412 verified
metadata
base_model:
  - Qwen/Qwen3-4B-Thinking-2507
  - Qwen/Qwen3-4B-Instruct-2507
library_name: transformers
tags:
  - mergekit
  - merge

merged_model_ties

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen3-4B-Instruct-2507 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


merge_method: ties
base_model: Qwen/Qwen3-4B-Instruct-2507

models:
  - model: Qwen/Qwen3-4B-Instruct-2507
  - model: Qwen/Qwen3-4B-Thinking-2507

parameters:
  density: 0.5        # tỷ lệ phần delta được giữ lại (0.3–0.7 là phổ biến)
  weight: 0.5         # trọng số giữa 2 model (50/50)
  normalize: true      # chuẩn hoá delta trước khi merge
  rescale: true        # cân bằng lại norm sau merge
dtype: bfloat16