bruhzair / proxy8

proxy8

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using /workspace/cache/models--TheSkullery--L3.1x3.3-Hydroblated-R1-70B-v5/snapshots/885b8ba1b37ca0ec5135b20c7ec4ed35441536f7 as a base.

Models Merged

The following models were included in the merge:

• /workspace/cache/models--bruhzair--group1-i/snapshots/6d8b2aa1af350ac3295ae2600dc8dd815ee82924
• /workspace/cache/models--bruhzair--group1-j/snapshots/98bf6acd93d951a835c1f059c7af73e2d8876f98
• /workspace/cache/models--bruhzair--group1-a/snapshots/2bee001a762db41f23359a017ad9fa0d5d4be9c5

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /workspace/cache/models--bruhzair--group1-a/snapshots/2bee001a762db41f23359a017ad9fa0d5d4be9c5
    parameters:
      weight: 0.25 
      density: 0.5
  - model: /workspace/cache/models--bruhzair--group1-i/snapshots/6d8b2aa1af350ac3295ae2600dc8dd815ee82924
    parameters:
      weight: 0.25
      density: 0.5
  - model: /workspace/cache/models--bruhzair--group1-j/snapshots/98bf6acd93d951a835c1f059c7af73e2d8876f98
    parameters:
      weight: 0.25
      density: 0.5
  - model: /workspace/cache/models--TheSkullery--L3.1x3.3-Hydroblated-R1-70B-v5/snapshots/885b8ba1b37ca0ec5135b20c7ec4ed35441536f7
    parameters:
      weight: 0.25
      density: 0.5
merge_method: dare_ties
base_model: /workspace/cache/models--TheSkullery--L3.1x3.3-Hydroblated-R1-70B-v5/snapshots/885b8ba1b37ca0ec5135b20c7ec4ed35441536f7
parameters:
  normalize: true
dtype: bfloat16
int8_mask: true
tokenizer:
 source: union