adami1/405M_TIES-merge_pile_300B_into_german_200B_from_pile_replay25_density-0.5
015
405MTIES-mergepile300Bintogerman200Bfrompilereplay25density-0.5
405MTIES-mergepile300Bintogerman200Bfrompilereplay25density-0.5 is a merge of the following models using mergekit:
๐งฉ Configuration
\```yamlmodels:
- model: btherien/JOB-3312838410Mit-86245tr-german-replay-25scratch # no parameters necessary for base model
- model: btherien/JOB-3150994410Mit-132366tr-pile-trainscratch parameters: density: 0.5 weight: 1.0 mergemethod: ties basemodel: btherien/JOB-3312838410Mit-86245tr-german-replay-25scratch parameters: normalize: true dtype: float16\```
