license: apache-2.0 | |
tags: | |
- merge | |
- mergekit | |
- lazymergekit | |
- TURKCELL/Turkcell-LLM-7b-v1 | |
- Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0 | |
# berke-tr-slerp-merge-7B | |
berke-tr-slerp-merge-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
* [TURKCELL/Turkcell-LLM-7b-v1](https://huggingface.co/TURKCELL/Turkcell-LLM-7b-v1) | |
* [Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0](https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0) | |
## Configs | |
\```yaml | |
slices: | |
- sources: | |
- model: TURKCELL/Turkcell-LLM-7b-v1 | |
layer_range: [0, 32] | |
- model: Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0 | |
layer_range: [0, 32] | |
merge_method: slerp | |
base_model: mistralai/Mistral-7B-Instruct-v0.2 | |
parameters: | |
t: | |
- filter: self_attn | |
value: [0, 0.5, 0.3, 0.7, 1] | |
- filter: mlp | |
value: [1, 0.5, 0.7, 0.7, 0.7] | |
- value: 0.7 | |
dtype: bfloat16 | |
\``` |