prototype-0.4x326

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

Merge Details

Merge Method

This model was merged using the Multi-SLERP merge method using /workspace/prototype-0.4x325 as a base.

Models Merged

The following models were included in the merge:

• /workspace/prototype-0.4x310
• /workspace/prototype-0.4x323
• /workspace/cache/models--bruhzair--prototype-0.4x301/snapshots/ba244ff497fd1a57c7954269c360a0f96e89f7a4
• /workspace/prototype-0.4x312

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /workspace/prototype-0.4x310
    parameters:
      weight: [0.25]
  - model: /workspace/prototype-0.4x312
    parameters:
      weight: [0.15]
  - model: /workspace/prototype-0.4x323
    parameters:
      weight: [0.25]
  - model: /workspace/cache/models--bruhzair--prototype-0.4x301/snapshots/ba244ff497fd1a57c7954269c360a0f96e89f7a4
    parameters:
      weight: [0.35]
base_model: /workspace/prototype-0.4x325
merge_method: multislerp
tokenizer:
  source: base
chat_template: llama3
parameters:
  normalize_weights: false
  eps: 1e-9
pad_to_multiple_of: 8
int8_mask: true
dtype: float32
out_dtype: bfloat16