Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 18
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/acc_MRL4096_ROLLOUT4_LR5e-7/global_step_54/actor/huggingface
parameters:
weight: 0.5
density: 0.2
- model: /local/scratch/zli2255/workspace/MergeExpert/checkpoints/baselines_openrs/accfmt_MRL4096_ROLLOUT4_LR5e-7/global_step_54/actor/huggingface
parameters:
weight: 0.5
density: 0.2
merge_method: ties
parameters:
normalize: true
dtype: bfloat16
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Base model
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B