|
--- |
|
base_model: |
|
- Qwen/Qwen2.5-Coder-32B-Instruct |
|
- NovaSky-AI/Sky-T1-32B-Flash |
|
- Qwen/Qwen2.5-Coder-32B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- qwen2 |
|
license: apache-2.0 |
|
--- |
|
# tomasmcm/sky-t1-coder-32b-flash |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
I wanted to see if it would be possible to improve on [FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview](https://huggingface.co./FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview) and [CoderO1-DeepSeekR1-Coder-32B-Preview](https://huggingface.co./RDson/CoderO1-DeepSeekR1-Coder-32B-Preview) by using [Sky-T1-32B-Flash](https://huggingface.co./NovaSky-AI/Sky-T1-32B-Flash) as the reasoning model that is merged with [Qwen2.5-Coder-32B-Instruct](https://huggingface.co./Qwen/Qwen2.5-Coder-32B-Instruct) instead of DeepSeek-R1-Distill-Qwen-32B. The idea is to have a strong coder model that can reason but without very long reasoning chains (hence using the Flash model). |
|
|
|
GGUF files available at [mradermacher/sky-t1-coder-32b-flash-GGUF](https://huggingface.co./mradermacher/sky-t1-coder-32b-flash-GGUF) (thank you!) |
|
|
|
## LLM Leaderboard (15 Mar 2025) |
|
|
|
| Rank | Model | Average | IFEval | BBH | MATH | GPQA | MUSR | MMLU-PRO | |
|
|------|--------|---------|---------|-----|------|------|------|-----------| |
|
| 22 | Qwen/Qwen2.5-32B-Instruct | **46.60%** | **83.46%** | **56.49%** | **62.54%** | 11.74% | 13.50% | 51.85% | |
|
| 39 | tomasmcm/sky-t1-coder-32b-flash | 44.87% | 77.80% | 55.47% | 54.23% | **15.77%** | 12.81% | **53.13%** | |
|
| 147 | huihuiai/QwQ-32B-Coder-Fusion-9010 | 41.58% | 57.78% | 53.02% | 53.17% | 14.88% | **19.52%** | 51.11% | |
|
| 276 | Qwen/Qwen2.5-Coder-32B-Instruct | 39.89% | 72.65% | 52.27% | 49.55% | 13.20% | 13.72% | 37.92% | |
|
| 717 | Qwen/QwQ-32B-Preview | 34.12% | 40.35% | 53.39% | 44.94% | 4.25% | 9.81% | 51.98% | |
|
| 2100 | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 22.96% | 41.86% | 17.15% | 17.07% | 4.59% | 16.14% | 40.96% | |
|
| 3574 | Qwen/QwQ-32B | 12.21% | 39.77% | 2.87% | 16.09% | 1.34% | 11.05% | 2.18% | |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-Coder-32B](https://huggingface.co./Qwen/Qwen2.5-Coder-32B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co./Qwen/Qwen2.5-Coder-32B-Instruct) |
|
* [NovaSky-AI/Sky-T1-32B-Flash](https://huggingface.co./NovaSky-AI/Sky-T1-32B-Flash) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
# Pivot model |
|
- model: Qwen/Qwen2.5-Coder-32B |
|
# Target models |
|
- model: Qwen/Qwen2.5-Coder-32B-Instruct |
|
- model: NovaSky-AI/Sky-T1-32B-Flash |
|
merge_method: sce |
|
base_model: Qwen/Qwen2.5-Coder-32B |
|
parameters: |
|
select_topk: 1.0 |
|
dtype: bfloat16 |
|
``` |
