|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1 |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberabeja |
|
--- |
|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberdeepseek |
|
--- |
|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: AXCXEPT/EZO-AutoCoTRAG-Qwen2.5-32B-Instruct |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberezo |
|
--- |
|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberfuze |
|
--- |
|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberfuzecoder |
|
--- |
|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: karakuri-ai/karakuri-lm-32b-thinking-2501-exp |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberkarakuri |
|
--- |
|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: Qwen/QwQ-32B-Preview |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberqwq |
|
--- |
|
merge_method: slerp |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
- model: NovaSky-AI/Sky-T1-32B-Flash |
|
parameters: |
|
t: 0.5 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberskyt1 |
|
--- |
|
merge_method: model_stock |
|
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
models: |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberabeja |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberdeepseek |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberezo |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberfuze |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberfuzecoder |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberkarakuri |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberqwq |
|
- model: RoguePlanet-DeepSeek-R1-Qwen-32B-preset-cyberskyt1 |
|
dtype: bfloat16 |
|
name: RoguePlanet-DeepSeek-R1-Qwen-32B |