mergekit-community/UltraLong-Thinking

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:

• mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1
• nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct
  - model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1
merge_method: slerp
base_model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers