| base_model: | |
| - autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1 | |
| - ank028/Llama-3.2-1B-Instruct-commonsense_qa | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| # c_l | |
| 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 SLERP merge method. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1](https://huggingface.co/autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1) | |
| * [ank028/Llama-3.2-1B-Instruct-commonsense_qa](https://huggingface.co/ank028/Llama-3.2-1B-Instruct-commonsense_qa) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| slices: | |
| - sources: | |
| - model: ank028/Llama-3.2-1B-Instruct-commonsense_qa | |
| layer_range: [0, 16] | |
| - model: autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1 | |
| layer_range: [0, 16] | |
| merge_method: slerp | |
| base_model: ank028/Llama-3.2-1B-Instruct-commonsense_qa | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0, 0.5, 0.3, 0.7, 1] | |
| - filter: mlp | |
| value: [1, 0.5, 0.7, 0.3, 0] | |
| - value: 0.5 # fallback for rest of tensors | |
| dtype: float16 | |
| name: Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-slerp | |
| ``` | |