| models: | |
| - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | |
| # Distilled version of DeepSeek-R1 fine-tuned from Qwen2.5-14B | |
| parameters: | |
| density: 0.5 | |
| weight: 0.3 | |
| - model: mathdong01/DeepSeek-R1-14B-Finetuned | |
| # Fine-tuned DeepSeek R1 model | |
| parameters: | |
| density: 0.5 | |
| weight: 0.2 | |
| - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 | |
| # Distilled model fine-tuned for specific tasks | |
| parameters: | |
| density: 0.6 | |
| weight: 0.3 | |
| merge_method: dare_ties | |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| dtype: bfloat16 |