CoderO1-DeepSeekR1-14B-Preview (Not limited to coding, it is just a name)

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

This is based on the work of FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Instruct-32B-Preview.

Merge Details

Merge Method

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

Models Merged

The following models were included in the merge:

• deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
• arcee-ai/Virtuoso-Small-v2
• Qwen/Qwen2.5-14B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: Qwen/Qwen2.5-14B
  # Target models
  - model: Qwen/Qwen2.5-14B-Instruct
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  - model: arcee-ai/Virtuoso-Small-v2
merge_method: sce
base_model: Qwen/Qwen2.5-14B
tokenizer:
  source: union
parameters:
  select_topk: 1.0
dtype: bfloat16