prototype-0.4x232

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

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using /workspace/prototype-0.4x229 as a base.

Models Merged

The following models were included in the merge:

• /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
• /workspace/cache/models--Sao10K--70B-L3.3-Cirrus-x1/snapshots/31d7ca33f3098d1eabe6f87a2c5b5bde85b20f35
• /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
• /workspace/cache/models--LatitudeGames--Wayfarer-Large-70B-Llama-3.3/snapshots/68cb7a33f692be64d4b146576838be85593a7459

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
    parameters:
      weight: 0.2
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
    parameters:
      weight: 0.2
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: /workspace/cache/models--LatitudeGames--Wayfarer-Large-70B-Llama-3.3/snapshots/68cb7a33f692be64d4b146576838be85593a7459
    parameters:
      weight: 0.2
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: /workspace/cache/models--Sao10K--70B-L3.3-Cirrus-x1/snapshots/31d7ca33f3098d1eabe6f87a2c5b5bde85b20f35
    parameters:
      weight: 0.2
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: /workspace/prototype-0.4x229
    parameters:
      weight: 0.2
      density: 0.7
      epsilon: 0.1
      lambda: 1.0
base_model: /workspace/prototype-0.4x229
merge_method: della_linear
tokenizer:
  source: base
parameters:
  normalize: false
pad_to_multiple_of: 8
int8_mask: true
dtype: bfloat16