Edit model card

405M_TIES-merge_pile_300B_into_german_200B_from_pile_replay25_density-0.95

405M_TIES-merge_pile_300B_into_german_200B_from_pile_replay25_density-0.95 is a merge of the following models using mergekit:

🧩 Configuration

```yamlmodels:

  • model: btherien/JOB-3312838_410M_it-86245_tr-german-replay-25_scratch

    no parameters necessary for base model

  • model: btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch parameters: density: 0.95 weight: 1.0 merge_method: ties base_model: btherien/JOB-3312838_410M_it-86245_tr-german-replay-25_scratch parameters: normalize: true dtype: float16```
Downloads last month
0
Safetensors
Model size
405M params
Tensor type
FP16
·
Inference API
This model can be loaded on Inference API (serverless).