attashe/q-2.5-deepseek-r1-veltha-v0.2

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:

• deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
• djuna/Q2.5-Veltha-14B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: djuna/Q2.5-Veltha-14B
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
merge_method: slerp
base_model: djuna/Q2.5-Veltha-14B
parameters:
  t:
    - filter: self_attn
      value: [0.2, 0.25, 0.3, 0.25, 0.2]
    - filter: "q_proj|k_proj|v_proj"
      value: [0.2, 0.25, 0.3, 0.25, 0.2]
    - filter: "up_proj|down_proj"
      value: [0.2, 0.3, 0.4, 0.3, 0.2]
    - filter: mlp
      value: [0.25, 0.35, 0.55, 0.35, 0.25]
    - value: 0.45  # default for other components
dtype: bfloat16