90dfaffd32
Model: Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties Source: Original Platform
15 lines
517 B
YAML
15 lines
517 B
YAML
models:
|
|
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/len_MRL4096_ROLLOUT4_LR5e-7/global_step_30/actor/huggingface
|
|
parameters:
|
|
weight: 0.5
|
|
density: 0.5
|
|
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/accfmt_MRL4096_ROLLOUT4_LR5e-7/global_step_54/actor/huggingface
|
|
parameters:
|
|
weight: 0.5
|
|
density: 0.5
|
|
merge_method: dare_ties
|
|
parameters:
|
|
normalize: true
|
|
dtype: bfloat16
|
|
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|