models: | |
- model: btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune | |
# no parameters necessary for base model | |
- model: btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch | |
parameters: | |
density: 0.75 | |
weight: 1.0 | |
merge_method: ties | |
base_model: btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune | |
parameters: | |
normalize: true | |
dtype: float16 |