Model Stock: All we need is just a few fine-tuned models
Paper
β’
2403.19522
β’
Published
β’
13
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: thirdeyeai/marco-o1-uncensored
- model: huihui-ai/UwU-7B-Instruct-abliterated
- model: huihui-ai/Marco-o1-abliterated
merge_method: model_stock
base_model: huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
normalize: false
int8_mask: true
dtype: bfloat16