appvoid/dot-v2.6

merge

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

Merge Details

Merge Method

This model was merged using the linear DARE merge method using appvoid/palmer-003 as a base.

Models Merged

The following models were included in the merge:

• TinyLlama/TinyLlama-1.1B-Chat-v1.0
• matlok/tinyllama-cinder-openhermes-32k
• BEE-spoke-data/TinyLlama-1.1bee
• microsoft/rho-math-1b-interpreter-v0.1
• ShieldX/manovyadh-1.1B-v1-chat
• raidhon/coven_tiny_1.1b_32k_orpo_alpha

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: BEE-spoke-data/TinyLlama-1.1bee
    parameters:
      density: 0.33
      weight: 0.50
  - model: raidhon/coven_tiny_1.1b_32k_orpo_alpha
    parameters:
      density: 0.36
      weight: 0.40
  - model: ShieldX/manovyadh-1.1B-v1-chat
    parameters:
      density: 0.33
      weight: 0.30
  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
    parameters:
      density: 0.40
      weight: 0.45
  - model: matlok/tinyllama-cinder-openhermes-32k
    parameters:
      density: 0.32
      weight: 0.26
  - model: microsoft/rho-math-1b-interpreter-v0.1
    parameters:
      density: 0.38
      weight: 0.35

merge_method: dare_linear
base_model: appvoid/palmer-003
parameters:
  normalize: false
  int8_mask: true
dtype: float16