models: | |
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | |
- model: Qwen/Qwen2.5-7B-Instruct | |
- model: Qwen/Qwen2.5-7B-Instruct+bunnycore/Qwen-2.5-7b-rp-lora | |
base_model: Qwen/Qwen2.5-7B-Instruct | |
merge_method: model_stock | |
parameters: | |
dtype: bfloat16 | |
tokenizer_source: Qwen/Qwen2.5-7B-Instruct | |