RDson's picture
Add files using upload-large-folder tool
b1add5a verified
---
base_model:
- arcee-ai/Virtuoso-Small-v2
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- arcee-ai/SuperNova-Medius
- Krystalan/DRT-o1-14B
library_name: transformers
tags:
- mergekit
- merge
---
# CoderO1-14B-Preview-v2
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [arcee-ai/Virtuoso-Small-v2](https://huggingface.co/arcee-ai/Virtuoso-Small-v2) as a base.
### Models Merged
The following models were included in the merge:
* [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)
* [arcee-ai/SuperNova-Medius](https://huggingface.co/arcee-ai/SuperNova-Medius)
* [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
# Pivot model
- model: arcee-ai/Virtuoso-Small-v2
# Target models
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- model: arcee-ai/SuperNova-Medius
- model: Krystalan/DRT-o1-14B
merge_method: sce
base_model: arcee-ai/Virtuoso-Small-v2
tokenizer:
source: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
parameters:
select_topk: 1.0
dtype: bfloat16
```