baselines / .gitattributes
fisherman611's picture
Upload folder using huggingface_hub
dd59dd2 verified
Raw
History Blame Contribute Delete
11.7 kB
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_0.6b_spider/e5-bs4-lr5e-05-G4-N2-NN1/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_0.6b_spider/e5-bs4-lr5e-05-G4-N2-NN1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_0.6b_spider/e5-bs4-lr5e-05-G4-N2-NN1/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_0.6b_spider/e5-bs4-lr5e-05-G4-N2-NN1/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_0.6b_spider/e5-bs4-lr5e-05-G4-N2-NN1/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_4b_spider_lora/e5-bs4-lr0.0001-G4-N2-NN1-lora-32-64-0.1/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_4b_spider_lora/e5-bs4-lr0.0001-G4-N2-NN1-lora-32-64-0.1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_4b_spider_lora/e5-bs4-lr0.0001-G4-N2-NN1-lora-32-64-0.1/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_4b_spider_lora/e5-bs4-lr0.0001-G4-N2-NN1-lora-32-64-0.1/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sft_sft_qwen3_4b_spider_lora/e5-bs4-lr0.0001-G4-N2-NN1-lora-32-64-0.1/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fkl_train_0.6b_4b_spider_lora/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fkl_train_0.6b_4b_spider_lora/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fkl_train_0.6b_4b_spider_lora/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fkl_train_0.6b_4b_spider_lora/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fkl_train_0.6b_4b_spider_lora/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_spider_lora/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_spider_lora/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_spider_lora/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_spider_lora/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_spider_lora/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sfkl_train_0.6b_4b_spider_lora/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sfkl_train_0.6b_4b_spider_lora/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sfkl_train_0.6b_4b_spider_lora/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sfkl_train_0.6b_4b_spider_lora/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/sfkl_train_0.6b_4b_spider_lora/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/srkl_train_0.6b_4b_spider_lora/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/srkl_train_0.6b_4b_spider_lora/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/srkl_train_0.6b_4b_spider_lora/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/srkl_train_0.6b_4b_spider_lora/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/srkl_train_0.6b_4b_spider_lora/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/amid_train_0.6b_4b_spider_ab_pr_0.5_0.5_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/amid_train_0.6b_4b_spider_ab_pr_0.5_0.5_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/amid_train_0.6b_4b_spider_ab_pr_0.5_0.5_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/amid_train_0.6b_4b_spider_ab_pr_0.5_0.5_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/amid_train_0.6b_4b_spider_ab_pr_0.5_0.5_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/distillm_train_0.6b_4b_spider_adaptive-srkl_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/distillm_train_0.6b_4b_spider_adaptive-srkl_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/distillm_train_0.6b_4b_spider_adaptive-srkl_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/distillm_train_0.6b_4b_spider_adaptive-srkl_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/distillm_train_0.6b_4b_spider_adaptive-srkl_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fdd_train_0.6b_4b_spider_sfkl_t33-36_s25-28_e5-bs2-lr0.0001-G8-N2-NN1-kd0.9-lora-16-64-0.1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_kd0.6_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.6-lora-16-64-0.1/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_kd0.6_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.6-lora-16-64-0.1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_kd0.6_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.6-lora-16-64-0.1/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_kd0.6_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.6-lora-16-64-0.1/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/csd_train_0.6b_4b_kd0.6_spider_e5-bs2-lr0.0001-G8-N2-NN1-kd0.6-lora-16-64-0.1/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fdd_train_0.6b_4b_spider_sfkl_t33-36_s25-28_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fdd_train_0.6b_4b_spider_sfkl_t33-36_s25-28_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fdd_train_0.6b_4b_spider_sfkl_t33-36_s25-28_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fdd_train_0.6b_4b_spider_sfkl_t33-36_s25-28_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/fdd_train_0.6b_4b_spider_sfkl_t33-36_s25-28_e5-bs2-lr0.0001-G8-N2-NN1-kd0.7-lora-16-64-0.1/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_kd0.6_spider_lora/1090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_kd0.6_spider_lora/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_kd0.6_spider_lora/436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_kd0.6_spider_lora/654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3/rkl_train_0.6b_4b_kd0.6_spider_lora/872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/checkpoints/epoch_1/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/checkpoints/epoch_1/88/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/checkpoints/epoch_2/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/checkpoints/epoch_3/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/checkpoints/epoch_4/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/checkpoints/epoch_5/218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/data/epoch_2/train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/data/epoch_3/train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/data/epoch_4/train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/data/epoch_5/train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/student_epoch_1.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/student_epoch_2.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/student_epoch_3.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/student_epoch_4.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/student_epoch_5.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/teacher_epoch_2.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/teacher_epoch_3.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/teacher_epoch_4.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/teacher_epoch_5.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/generated/teacher_train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/processed/epoch_2/qwen/train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/processed/epoch_3/qwen/train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/processed/epoch_4/qwen/train.jsonl filter=lfs diff=lfs merge=lfs -text
distillm2/spider_qwen3_0.6b_4b_paper_full/processed/epoch_5/qwen/train.jsonl filter=lfs diff=lfs merge=lfs -text
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-1095/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text