sxiong/MLR_sft_data download history
sxiong/MLR_sft_data is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 112 times (18 in the last 7 days), and 265 times in total. It ranks #138,484 among datasets by monthly downloads.
MLR SFT Data MLR SFT Data is a teacher-generated supervised fine-tuning dataset for training Multi-Level Reasoning (MLR) models in the paper Enhancing Language Model Reasoning with Structured Multi-Level Modeling (ICLR 2026). It decomposes complete reasoning trajectories into two type
Models trained on MLR_sft_data
7 models list it as training data.
- mradermacher/MLR_executor_Qwen-7B-GGUF 742 downloads in 30 days
- sxiong/MLR_executor_Qwen-7B 729 downloads in 30 days
- sxiong/MLR_executor_Llama-8B 700 downloads in 30 days
- sxiong/MLR_planner_Qwen-7B-LoRA 23 downloads in 30 days
- sxiong/MLR_executor_Qwen-1.5B 20 downloads in 30 days
- sxiong/MLR_planner_Llama-8B-LoRA 19 downloads in 30 days
- sxiong/MLR_planner_Qwen-1.5B-LoRA 11 downloads in 30 days
Open sxiong/MLR_sft_data on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.