CoolFace
Modelpublic

adami1/405M_TIES-merge_pile_300B_into_german_200B_from_pile_replay25_density-0.5

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes15downloads
Model Card

405MTIES-mergepile300Bintogerman200Bfrompilereplay25density-0.5

405MTIES-mergepile300Bintogerman200Bfrompilereplay25density-0.5 is a merge of the following models using mergekit:

๐Ÿงฉ Configuration

\```yamlmodels:

  • โ€”model: btherien/JOB-3312838410Mit-86245tr-german-replay-25scratch # no parameters necessary for base model
  • โ€”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\```