Files
Kepler-8B-Instruct/mergekit_config.yml

15 lines
302 B
YAML
Raw Normal View History

models:
- model: Qwen/Qwen2.5-7B-Instruct
parameters:
density: 1.0
weight: 0.6
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
parameters:
density: 0.5
weight: 0.4
merge_method: dare_ties
base_model: Qwen/Qwen2.5-7B-Instruct
dtype: bfloat16
tokenizer_source: base