After some success with my merging my favorite Llama 3 models, I decided to try my hand on some Qwen 2.5 models I have tried and enjoyed. I never quite got fully onto the Qwen bandwagon as I always preferred LLaMa, but a lot of folks swear by Qwen. In my limited experience with Qwen I have enjoyed these models and merged something decent I think. For this merge I went for a model stock merge.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Model Stock merge method using
zetasepic/Qwen2.5-72B-Instruct-abliterated as a base.
1base_model: zetasepic/Qwen2.5-72B-Instruct-abliterated
2merge_method: model_stock
3dtype: bfloat16
4models:
5 - model: spow12/ChatWaifu_72B_v2.2
6 - model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
7 - model: Steelskull/Q2.5-MS-Mistoria-72b-v2
8 - model: Sao10K/72B-Qwen2.5-Kunou-v1
9parameters:
10 filter_wise: false
11 normalize: false
12 int8_mask: true
