| base_model: | |
| - nitky/EZO-QwQ-32B-Preview | |
| - Saxo/Linkbricks-Horizon-AI-Japanese-Base-32B | |
| - huihui-ai/QwQ-32B-Preview-abliterated | |
| - Qwen/QwQ-32B-Preview | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| # Linkbricks-Horizon-AI-Japanese-Advanced-V1-32B | |
| This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). | |
| ## Merge Details | |
| ### Merge Method | |
| This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [nitky/EZO-QwQ-32B-Preview](https://huggingface.co/nitky/EZO-QwQ-32B-Preview) | |
| * [Saxo/Linkbricks-Horizon-AI-Japanese-Base-32B](https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Japanese-Base-32B) | |
| * [huihui-ai/QwQ-32B-Preview-abliterated](https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| base_model: Qwen/QwQ-32B-Preview | |
| dtype: bfloat16 | |
| merge_method: dare_ties | |
| parameters: | |
| int8_mask: 1.0 | |
| slices: | |
| - sources: | |
| - layer_range: [0, 64] | |
| model: Qwen/QwQ-32B-Preview | |
| - layer_range: [0, 64] | |
| model: Saxo/Linkbricks-Horizon-AI-Japanese-Base-32B | |
| parameters: | |
| density: 0.53 | |
| weight: 0.3 | |
| - layer_range: [0, 64] | |
| model: huihui-ai/QwQ-32B-Preview-abliterated | |
| parameters: | |
| density: 0.53 | |
| weight: 0.4 | |
| - layer_range: [0, 64] | |
| model: nitky/EZO-QwQ-32B-Preview | |
| parameters: | |
| density: 0.53 | |
| weight: 0.3 | |
| tokenizer_source: union | |
| ``` | |