bruhzair / Alpha-Model-1b-105B

alpha-model-1b

Alpha-Model-1c Q4 quants are in here by mistake. Planning on fixing later

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/test-model-13 as a base.

Models Merged

The following models were included in the merge:

• /workspace/test-model-4
• /workspace/test-model-6
• /workspace/test-model-11
• /workspace/test-model-14

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /workspace/test-model-11
    parameters:
      weight: 0.2
      density: 0.5
  - model: /workspace/test-model-14
    parameters:
      weight: 0.2
      density: 0.5
  - model: /workspace/test-model-6
    parameters:
      weight: 0.2
      density: 0.5
  - model: /workspace/test-model-4
    parameters:
      weight: 0.2
      density: 0.5
  - model: /workspace/test-model-13
    parameters:
      weight: 0.2
      density: 0.5
merge_method: dare_ties
base_model: /workspace/test-model-13
parameters:
  normalize: false
dtype: float32
out_dtype: bfloat16
tokenizer:
 source: base