| Mistral 7B trained for 0.1 epoch on https://huggingface.co/datasets/Magpie-Align/Magpie-Qwen2.5-Pro-1M-v0.1 using LoRA+ in unsloth. |
| Mistral 7B trained for 0.1 epoch on https://huggingface.co/datasets/Magpie-Align/Magpie-Qwen2.5-Pro-1M-v0.1 using LoRA+ in unsloth. |