| slices: | |
| - sources: | |
| - model: LeroyDyer/Mixtral_AI_CyberBrain_2.0 | |
| layer_range: [0, 32] | |
| - model: ezelikman/quietstar-8-ahead | |
| layer_range: [0, 32] | |
| # or, the equivalent models: syntax: | |
| # models: | |
| # - model: mistralai/Mistral-7B-Instruct-v0.2 | |
| # LaRGER MODEL MUST BE BASE or | |
| # BASE MODEL MUST BE THE TOKENIZER YOU WISH TO ADOPT | |
| # so for models with customized processes they must be the base model | |
| # If the base model has remote code then this must be collected and added | |
| # to the repo after and the config file adusted to allow for automapping to your new repo | |
| # - model: yanismiraoui/Yarn-Mistral-7b-128k-sharded | |
| merge_method: slerp | |
| base_model: ezelikman/quietstar-8-ahead | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0.3, 0.6, 0.3786, 0.6, 0.6] | |
| - filter: mlp | |
| value: [0.7, 0.4, 0.6, 0.4, 0.7] | |
| - value: 0.5 # fallback for rest of tensors | |
| dtype: float16 | |