| models: | |
| - model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B | |
| - model: hotmailuser/Llama3.3slerp1-70B | |
| merge_method: slerp | |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B | |
| dtype: bfloat16 | |
| parameters: | |
| t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers | |