Files
YOYO-O1-14B-V2/README.md

56 lines
1.7 KiB
Markdown
Raw Permalink Normal View History

---
base_model:
- deepcogito/cogito-v1-preview-qwen-14B
- Zhihu-ai/Zhi-Create-DSR1-14B
- agentica-org/DeepCoder-14B-Preview
- FractalAIResearch/Fathom-R1-14B
- arcee-ai/Virtuoso-Small-v2
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
language:
- en
- zh
pipeline_tag: text-generation
---
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e174e202fa032de4143324/GNPQMcj3XRXlXy3ebsPRZ.jpeg)
# YOYO-O1-14B-V2
*Combined the most top-notch 14B **inference** model and **code** model in the entire open-source community.*
### 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:
* [deepcogito/cogito-v1-preview-qwen-14B](https://huggingface.co/deepcogito/cogito-v1-preview-qwen-14B)
* [Zhihu-ai/Zhi-Create-DSR1-14B](https://huggingface.co/Zhihu-ai/Zhi-Create-DSR1-14B)
* [agentica-org/DeepCoder-14B-Preview](https://huggingface.co/agentica-org/DeepCoder-14B-Preview)
* [FractalAIResearch/Fathom-R1-14B](https://huggingface.co/FractalAIResearch/Fathom-R1-14B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: sce
models:
# Pivot model
- model: arcee-ai/Virtuoso-Small-v2 #knowledge
# Target models
- model: agentica-org/DeepCoder-14B-Preview #coding
- model: FractalAIResearch/Fathom-R1-14B #logic
- model: Zhihu-ai/Zhi-Create-DSR1-14B #creative writing
- model: deepcogito/cogito-v1-preview-qwen-14B #chat assistant
base_model: arcee-ai/Virtuoso-Small-v2 #knowledge
parameters:
select_topk: 1
dtype: bfloat16
normalize: true
int8_mask: true
```