Files
merge-test-2-sibling-violation/mergekit_config.yml

20 lines
460 B
YAML
Raw Normal View History

merge_method: della
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
dtype: bfloat16
models:
- model: nvidia/OpenMath-Nemotron-1.5B
parameters:
weight: 1.0
density: 0.6
epsilon: 0.3
- model: nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
parameters:
weight: 1.0
density: 0.6
epsilon: 0.3
- model: Fate-Zero/Archer2.0-Code-1.5B-Preview
parameters:
weight: 1.0
density: 0.6
epsilon: 0.3