Fused-DeepSeek-R1-14B-SFT288-RL56

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 deepseek-ai/DeepSeek-R1-Distill-Qwen-14B as a base.

Models Merged

The following models were included in the merge:

• radna/r1-14B-SFT-288
• radna/r1-14B-RL-56

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  # Target models
  - model: radna/r1-14B-SFT-288
  - model: radna/r1-14B-RL-56
merge_method: sce
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
parameters:
  select_topk: 1.0
dtype: bfloat16