appvoid/dot-v2.1

merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T as a base.

Models Merged

The following models were included in the merge:

• sreeramajay/TinyLlama-1.1B-orca-v1.0
• ShieldX/manovyadh-1.1B-v1-chat
• l3utterfly/tinyllama-1.1b-layla-v4
• AIGym/TinyLlama-1.1B-2.5T-chat-and-function-calling
• TinyLlama/TinyLlama-1.1B-Chat-v1.0
• vihangd/DopeyTinyLlama-1.1B-v1
• raidhon/coven_tiny_1.1b_32k_orpo_alpha
• appvoid/palmer-003

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: vihangd/DopeyTinyLlama-1.1B-v1
    parameters:
      density: 0.50
      weight: 0.50
  - model: raidhon/coven_tiny_1.1b_32k_orpo_alpha
    parameters:
      density: 0.66
      weight: 0.26
  - model: l3utterfly/tinyllama-1.1b-layla-v4
    parameters:
      density: 0.30
      weight: 0.125
  - model: ShieldX/manovyadh-1.1B-v1-chat
    parameters:
      density: 0.18
      weight: 0.125
  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
    parameters:
      density: 0.40
      weight: 0.25
  - model: sreeramajay/TinyLlama-1.1B-orca-v1.0
    parameters:
      density: 0.35
      weight: 0.37
  - model: AIGym/TinyLlama-1.1B-2.5T-chat-and-function-calling
    parameters:
      density: 0.25
      weight: 0.26
  - model: appvoid/palmer-003
    parameters:
      density: 0.90
      weight: 0.75

merge_method: task_arithmetic
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
parameters:
  normalize: false
  int8_mask: true
dtype: float16