merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: Qwen/Qwen2.5-72B-Instruct
    layer_range:
    - 0
    - 80
  - model: MaziyarPanahi/calme-2.1-qwen2.5-72b
    layer_range:
    - 0
    - 80
merge_method: slerp
base_model: Qwen/Qwen2.5-72B-Instruct
parameters:
  t:
  - filter: self_attn
    value: 0.5
  - filter: mlp
    value: 0.5
  - value: 0.5
dtype: bfloat16
tensor_parallel_devices: auto
allow_different_heads: true
Downloads last month
24
Safetensors
Model size
72.7B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for lkoenig/BBAI_72B_QwenMazi