bruhzair / prototype0.4x61

prototype-0.4x61

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/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3 as a base.

Models Merged

The following models were included in the merge:

• /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Nexus/snapshots/1fc6f9b78d8921a26003edb06a292e94488a4c52
• /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb
• /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-3.6/snapshots/caf3a6e92189ac5e2479d93eee50e4e57d87dadc

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-3.6/snapshots/caf3a6e92189ac5e2479d93eee50e4e57d87dadc
    parameters:
      select_topk: 0.1
  - model: /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb
    parameters:
      select_topk: 0.25
  - model: /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3
    parameters:
      select_topk: 0.5
  - model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Nexus/snapshots/1fc6f9b78d8921a26003edb06a292e94488a4c52
    parameters:
      select_topk: 0.7
base_model: /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3
merge_method: sce
tokenizer:
  source: union
chat_template: llama3
int8_mask: true
dtype: bfloat16