| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - rinna/bilingual-gpt-neox-4b | |
| - rinna/japanese-gpt-neox-3.6b | |
| # without_japanese_bilingual-gpt-neox_4b_task_arithmetic | |
| without_japanese_bilingual-gpt-neox_4b_task_arithmetic is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [rinna/bilingual-gpt-neox-4b](https://huggingface.co/rinna/bilingual-gpt-neox-4b) | |
| * [rinna/japanese-gpt-neox-3.6b](https://huggingface.co/rinna/japanese-gpt-neox-3.6b) | |
| ## 🧩 Configuration | |
| ```yaml | |
| models: | |
| - model: rinna/bilingual-gpt-neox-4b | |
| parameters: | |
| weight: 0.5 | |
| - model: rinna/japanese-gpt-neox-3.6b | |
| parameters: | |
| weight: 0.5 | |
| merge_method: task_arithmetic | |
| base_model: rinna/bilingual-gpt-neox-4b | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| dtype: bfloat16 | |
| ``` |