10B_TIES-merge_slimp_300B_into_pile_300B_density-0.75
10B_TIES-merge_slimp_300B_into_pile_300B_density-0.75 is a merge of the following models using mergekit:
🧩 Configuration
```yamlmodels:
- model: btherien/Model_-7-1B_It_-132366_Tr_-pile-train_scratch
no parameters necessary for base model
- model: btherien/Model_-7-1B_It_-132366_Tr_-slim-pajama-300B_scratch parameters: density: 0.75 weight: 1.0 merge_method: ties base_model: btherien/Model_-7-1B_It_-132366_Tr_-pile-train_scratch parameters: normalize: true dtype: float16```
- Downloads last month
- 7