# Main configuration for merging pre-trained models | |
models: | |
# - model: Intel/neural-chat-7b-v3-3 | |
# parameters: | |
# density: 0.9 # High density since generally good for most tasks | |
# weight: 0.4 # Lower weight compared to openchat due to slight inferiority | |
- model: meta-math/MetaMath-Mistral-7B | |
parameters: | |
density: 0.6 # Moderate density focusing mainly on mathematical prowess | |
weight: | |
- filter: mlp | |
value: 0.5 | |
- value: 0 | |
- model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser | |
parameters: | |
density: 0.8 # Balanced density emphasizing coding skills over chitchat | |
weight: 0.4 # Slightly higher weight acknowledging superior coding ability | |
base_model: Intel/neural-chat-7b-v3-3 | |
merge_method: ties | |
parameters: | |
normalize: true | |
int8_mask: false | |
dtype: float16 |