Downloads · 30 days
32
43% of all-time downloads
ldhldh/merged-qwen-omni-dare
merged-qwen-omni-dare is a machine learning model from ldhldh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This is a merge of pre-trained language models created using mergekit.
Downloads · 30 days
32
43% of all-time downloads
All-time downloads
75
Public
Parameters
635M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 99%
From the Hugging Face model README
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using Qwen/Qwen2.5-Omni-7B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
# mergekit 설정 파일: Qwen/Qwen3-8B 와 Qwen/Qwen2.5-Omni-7B 를 DARE_TIES 방식으로 병합
# 합칠 모델 목록
models:
- model: Qwen/Qwen2-Audio-7B
parameters:
weight: 1.0
density: 1.0
- model: Qwen/Qwen2.5-Omni-7B
parameters:
weight: 1.0
density: 1.0
merge_method: dare_ties
base_model: Qwen/Qwen2.5-Omni-7B # 또는 Qwen/Qwen3-8B
parameters:
density: 0.5 # 이 값을 조정하며 실험하세요 (예: 0.2, 0.7 등)
normalize: false
int8_mask: true
dtype: bfloat16