---
base_model:
- YOYO-AI/YOYO-O1-14B
tags:
- mergekit
- merge
license: apache-2.0
language:
- en
- zh
pipeline_tag: text-generation
library_name: exllamav2
---
# YOYO-O1-14B-exl2
Original model: [YOYO-O1-14B](https://huggingface.co/YOYO-AI/YOYO-O1-14B) by [YOYO-AI](https://huggingface.co/YOYO-AI)  
Foundation model: [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) by [Qwen](https://huggingface.co/Qwen)
## Quants
[4bpw h6 (main)](https://huggingface.co/cgus/YOYO-O1-14B-exl2/tree/main)  
[4.5bpw h6](https://huggingface.co/cgus/YOYO-O1-14B-exl2/tree/4.5bpw-h6)  
[5bpw h6](https://huggingface.co/cgus/YOYO-O1-14B-exl2/tree/5bpw-h6)  
[6bpw h6](https://huggingface.co/cgus/YOYO-O1-14B-exl2/tree/6bpw-h6)  
[8bpw h8](https://huggingface.co/cgus/YOYO-O1-14B-exl2/tree/8bpw-h8)  
## Quantization notes
Made with Exllamav2 0.2.8 with default dataset.  
These quants can be used with TabbyAPI or Text-Generation-WebUI with RTX GPU (Windows) or RTX/ROCm (Linux).  
Quants have to fit your VRAM, if you need RAM offloading then choose GGUF quants instead.
# Original model card
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e174e202fa032de4143324/GNPQMcj3XRXlXy3ebsPRZ.jpeg)

# YOYO-O1-14B

*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 [Qwen/Qwen2.5-Coder-14B](https://huggingface.co/Qwen/Qwen2.5-Coder-14B) as a base.

### Models Merged

The following models were included in the merge:
* [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct)
* [Gen-Verse/ReasonFlux-F1-14B](https://huggingface.co/Gen-Verse/ReasonFlux-F1-14B)
* [agentica-org/DeepCoder-14B-Preview](https://huggingface.co/agentica-org/DeepCoder-14B-Preview)
* [qihoo360/Light-R1-14B-DS](https://huggingface.co/qihoo360/Light-R1-14B-DS)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: sce
models:
  # Pivot model
  - model: Qwen/Qwen2.5-Coder-14B
  # Target models
  - model: agentica-org/DeepCoder-14B-Preview
  - model: qihoo360/Light-R1-14B-DS
  - model: Gen-Verse/ReasonFlux-F1-14B
  - model: Qwen/Qwen2.5-Coder-14B-Instruct
base_model: Qwen/Qwen2.5-Coder-14B
parameters:
  select_topk: 1
dtype: float16
tokenizer_source: qihoo360/Light-R1-14B-DS
normalize: true
int8_mask: true
```