sdar
Datasets
All datasets matching “sdar”WebShop-Qwen3-8B-SDAR-evalsd-artistic-facesSDAR1.7B_EB_Decode_1024_datasetSDAR-4B-Chat-MATH-Trajectories
SDAR-4B-Chat MATH Trajectories
Self-distillation trajectory data generated by SDAR-4B-Chat on the MATH training set, used for training T3D (Trajectory Self-Distillation with Direct Discriminative Optimization).
Paper: T3D: Few-Step Diffusion Language Models via Trajectory Self-Distillation with Direct Discriminative Optimization
Code: https://github.com/Tyrion58/T3D
Dataset Description
This dataset contains 8,523 samples from the MATH training set, each augmented with… See the full description on the dataset page: https://huggingface.co/datasets/Tyrion279/SDAR-4B-Chat-MATH-Trajectories.sdar-llama-factory-dataThe dataset_info.json contains all available datasets. If you are using a custom dataset, please make sure to add a dataset description in dataset_info.json and specify dataset: dataset_name before training to use it.
The dataset_info.json file should be put in the dataset_dir directory. You can change dataset_dir to use another directory. The default value is ./data.
Currently we support datasets in alpaca and sharegpt format. Allowed file types include json, jsonl, csv, parquet, arrow.… See the full description on the dataset page: https://huggingface.co/datasets/loongyy/sdar-llama-factory-data.sdar_4b_webshop_sft_ckpt
sdar_4b_webshop_bs4_eighth_reason_epoch1
This model is a fine-tuned version of /home/hal-yuyangq/Codes/efficient-verl-agent-lyy/SDAR/training/model/SDAR-4B-Chat on the sdar_webshop_bs4_eighth_reason dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The… See the full description on the dataset page: https://huggingface.co/datasets/loongyy/sdar_4b_webshop_sft_ckpt.