2beff19843
Model: Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties Source: Original Platform
15 lines
512 B
YAML
15 lines
512 B
YAML
models:
|
|
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/cos_MRL4096_ROLLOUT4_LR2e-6/global_step_40/actor/huggingface
|
|
parameters:
|
|
weight: 0.5
|
|
density: 0.5
|
|
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/accfmt_MRL4096_ROLLOUT4_LR2e-6/global_step_30/actor/huggingface
|
|
parameters:
|
|
weight: 0.5
|
|
density: 0.5
|
|
merge_method: ties
|
|
parameters:
|
|
normalize: true
|
|
dtype: bfloat16
|
|
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|