| *.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 | |
| grpo_sft-qwen3-4b-base-seqlen-16384-bs-128-lr-1e-5-wd-0.01-ds-synthetic-2-qwen_seqlen_8192_bs_128_micro_bs_1_lr_1e-5_dapo-math-17k-dedup/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| grpo_sft_qwen3-4b-base_seqlen_16384_bs_128_lr_3e-5_wd_0.01_ds_synthetic-2_qwen3-8b_8192_sft-global-step-7_seqlen_8192_bs_128_lr_1e-5_data_dapo-math-17k-small-processed-parquet/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| grpo_is-qwen3-4b-base-beh-qwen3-8b-seqlen-16384-bs-128-lr-1e-5-ds-synthetic__eff-1.0-nmode-flip-chunksize-1_seqlen_16384_epochs_2_bs_128_micro_bs_1_lr_1e-6_dapo-math-17k-dedup/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| grpo_is-qwen3-4b-base-beh-qwen3-8b-seqlen-16384-bs-128-lr-3e-5-ds-synthetic-2-sft-verified-merged-json-dm_seqlen_8192_bs_128_lr_1e-5_data_dapo-math-17k-small-processed-parquet/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| grpo_sft-qwen3-8b-base-seqlen-16384-bs-128-lr-1e-5-wd-0.01-ds-synthetic-2-qwen_seqlen_8192_bs_128_micro_bs_1_lr_1e-5_dapo-math-17k-dedup/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| grpo_sft_qwen3-8b-base_seqlen_16384_bs_128_lr_3e-5_wd_0.01_ds_synthetic-2_qwen3-8b_8192_sft-global-step-7_seqlen_8192_bs_128_lr_1e-5_data_dapo-math-17k-small-processed-parquet/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| grpo_is-qwen3-4b-base-beh-qwen3-8b-seqlen-16384-bs-128-lr-1e-5-ds-synthetic-2-qwen-dm--0.08-dm-0.3-g-0.99_seqlen_8192_bs_128_micro_bs_1_lr_1e-5_dapo-math-17k-dedup/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| grpo_is-qwen3-8b-base-beh-qwen3-8b-seqlen-16384-bs-128-lr-3e-5-ds-synthetic-2-qwen3-8b-8192-sft-dm--0.08-_seqlen_8192_bs_128_micro_bs_1_lr_1e-5_data_dapo-math-17k-small-processed-parquet/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| sft_qwen3-8b-base_seqlen_16384_bs_128_lr_1e-5_wd_0.01_ds_synthetic-2-qwen/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| sft_qwen3-8b-base_seqlen_16384_bs_128_lr_3e-5_wd_0.01_ds_synthetic-2_qwen3-8b_8192_sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| is_qwen3-8b-base_beh_qwen3-8b_seqlen_16384_bs_1_lr_3e-5_ds_synthetic-2-qwen_dm_-0.08_func_importance-sampling-weight-logspace_dM_0.3_g_0.999_ncoeff_1.0_nmode_flip_chunksize_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |