| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged | |
| - TifTifR/SFT-qa-Llama-3.1-8B-Instruct-20-r16-1_merged | |
| # SFT-dk-qa-Llama-3.1-8B-Instruct | |
| SFT-dk-qa-Llama-3.1-8B-Instruct is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged](https://huggingface.co/TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged) | |
| * [TifTifR/SFT-qa-Llama-3.1-8B-Instruct-20-r16-1_merged](https://huggingface.co/TifTifR/SFT-qa-Llama-3.1-8B-Instruct-20-r16-1_merged) | |
| ## 🧩 Configuration | |
| ```yaml | |
| models: | |
| - model: TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged | |
| parameters: | |
| weight: 0.5 | |
| - model: TifTifR/SFT-qa-Llama-3.1-8B-Instruct-20-r16-1_merged | |
| parameters: | |
| weight: 0.5 | |
| base_model: TifTifR/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged | |
| merge_method: task_arithmetic | |
| dtype: float16 | |
| ``` |