prototype-0.4x152

prototype-0.4x152

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SCE merge method using /workspace/prototype-0.4x149 as a base.

Models Merged

The following models were included in the merge:

• /workspace/cache/models--TheDrummer--Anubis-70B-v1/snapshots/e50d699bf6c21afcf4dbd9a8b4f73511b0366efb
• /workspace/cache/models--LatitudeGames--Wayfarer-Large-70B-Llama-3.3/snapshots/68cb7a33f692be64d4b146576838be85593a7459
• /workspace/cache/models--Delta-Vector--Austral-70B-Preview/snapshots/bf62fe4ffd7e460dfa3bb881913bdfbd9dd14002

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /workspace/cache/models--Delta-Vector--Austral-70B-Preview/snapshots/bf62fe4ffd7e460dfa3bb881913bdfbd9dd14002
    parameters:
      select_topk: 0.15
  - model: /workspace/cache/models--LatitudeGames--Wayfarer-Large-70B-Llama-3.3/snapshots/68cb7a33f692be64d4b146576838be85593a7459
    parameters:
      select_topk: 0.1
  - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1/snapshots/e50d699bf6c21afcf4dbd9a8b4f73511b0366efb
    parameters:
      select_topk: 0.15
  - model: /workspace/prototype-0.4x149
    parameters:
      select_topk: 0.75
base_model: /workspace/prototype-0.4x149
merge_method: sce
tokenizer:
  source: base
int8_mask: true
dtype: bfloat16