Files
group_model/mergekit_config.yml

17 lines
472 B
YAML
Raw Permalink Normal View History

merge_method: task_arithmetic
base_model: checkpoints/Qwen3-1.7B-baseline
models:
- model: checkpoints/math_model/best_model
parameters:
weight: 0.25
- model: checkpoints/safety_model/best_model_sft_dpo/hf_model
parameters:
weight: 0.25
- model: checkpoints/general_knowledge_model/full_sft
parameters:
weight: 0.25
- model: checkpoints/multilinguality_model/sft_multilingual_v16_nonthinking_1e-4_warmup0p1
parameters:
weight: 0.25
dtype: bfloat16