TimeLordRaps/DS-R1-Lamarckvergence-14B-1M-test3

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using Qwen/Qwen2.5-14B-Instruct-1M as a base.

Models Merged

The following models were included in the merge:

• Triangle104/DS-R1-Distill-Q2.5-14B-Harmony_V0.1
• deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
• suayptalha/Lamarckvergence-14B

Configuration

The following YAML configuration was used to produce this model:

merge_method: sce
base_model: Qwen/Qwen2.5-14B-Instruct-1M
models:
  - model: Qwen/Qwen2.5-14B-Instruct-1M
    parameters:
      weight: 0.7
  - model: Triangle104/DS-R1-Distill-Q2.5-14B-Harmony_V0.1
    parameters:
      weight: 0.05
  - model: suayptalha/Lamarckvergence-14B
    parameters:
      weight: 0.2
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
    parameters:
      weight: 0.05
parameters:
  density: 0.4
  select_topk: 0.2
  normalize: true
dtype: bfloat16
tokenizer_source: Triangle104/DS-R1-Distill-Q2.5-14B-Harmony_V0.1