*.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 26_01_16_qwen3-vl-2b_sft_teacher_is_correct_reasoning/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_01_16_qwen3-vl-2b_sft_teacher_is_correct_reasoning/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_01_18_distill_2b_4b_teacher_is_correct_revision_120steps/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_01_18_distill_2b_4b_teacher_is_correct_revision_120steps/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_01_18_distill_2b_4b_all_reasoning_80steps/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_04_distill_2b_4b_reasoning_long_length_all_80steps/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_15_distill_2b_4b_student_on_policy_all_80steps/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_15_distill_2b_4b_student_on_policy_all_40steps/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_15_distill_2b_4b_student_on_policy_only_distill_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_15_distill_2b_4b_student_on_policy_only_distill_80steps/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_15_distill_2b_4b_student_on_policy_forward_80steps/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_22_off_policy_distill_2b_8b_correct_2epoch/checkpoint-37/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_22_off_policy_distill_2b_8b_correct_2epoch/checkpoint-74/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_22_off_policy_distill_2b_8b_correct_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_23_off_policy_distill_2b_4b_correct_2epoch/checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_23_off_policy_distill_2b_4b_correct_2epoch/checkpoint-72/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_02_23_off_policy_distill_2b_4b_correct_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_11_distill_2b_8b_off_policy_per_4d_attn_uniform_masking_target_attn_relative_04_2epoch/checkpoint-37/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_11_distill_2b_8b_off_policy_per_4d_attn_uniform_masking_target_attn_relative_04_2epoch/checkpoint-74/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_11_distill_2b_8b_off_policy_per_4d_attn_uniform_masking_target_attn_relative_04_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_11_distill_2b_8b_off_policy_per_4d_attn_uniform_masking_01_1_2epoch/checkpoint-37/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_11_distill_2b_8b_off_policy_per_4d_attn_uniform_masking_01_1_2epoch/checkpoint-74/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_11_distill_2b_8b_off_policy_per_4d_attn_uniform_masking_01_1_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_05_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_01_1_2epoch/checkpoint-37/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_16_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_target_attn_kl_consistency_03_05_1_05_2_3epoch/checkpoint-111/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_16_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_target_attn_kl_consistency_03_05_1_05_2_3epoch/checkpoint-37/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_16_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_target_attn_kl_consistency_03_05_1_05_2_3epoch/checkpoint-74/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_16_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_target_attn_kl_consistency_03_05_1_05_2_3epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_16_distill_2b_8b_off_policy_thinking_4096_2epoch/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_16_distill_2b_8b_off_policy_thinking_4096_2epoch/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_16_distill_2b_8b_off_policy_thinking_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_18_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_target_attn_kl_03_05_05_2_thinking_4096_2epoch_a100/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_18_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_target_attn_kl_03_05_05_2_thinking_4096_2epoch_a100/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_03_18_distill_2b_8b_off_policy_per_4d_attn_not_uniform_masking_target_attn_kl_03_05_05_2_thinking_4096_2epoch_a100/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b__grpo_thinking__fix_reward__DEBUG_ep2_rb384_gb128/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b__thinking__grpo__papo__fix_reward__REC_ENV_EXP_kl_prcp_0.01__ep2_rb384_gb128/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b__grpo_with_kd__thinking__ep2_rb384_gb128_kdcoef1.0_tau0.3_0.5/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b__thinking__grpo__papo_with_kd__fix_reward__kl_prcp_0.01__kdcoef1.0_tau0.3_0.5__ep2_rb384_gb128/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b__grpo_with_vold__thinking__ep2_rb384_gb128_kdcoef1.0e-3/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_s1k_on_policy_1epoch/checkpoint-19/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_s1k_on_policy_1epoch/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_s1k_on_policy_1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_onpolicy_1epoch/checkpoint-23/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_onpolicy_1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_onpolicy_with_ours_2epoch/checkpoint-23/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_onpolicy_with_ours_2epoch/checkpoint-46/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_onpolicy_with_ours_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_off_policy_ours_2epoch/checkpoint-23/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_off_policy_ours_2epoch/checkpoint-46/tokenizer.json filter=lfs diff=lfs merge=lfs -text llm_distill_2b_9b_stratos17k_off_policy_ours_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_06_self_distill_2b_ours_4096_2epoch/checkpoint-20/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_06_self_distill_2b_ours_4096_2epoch/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_06_self_distill_2b_ours_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b_grpo_ref_attn_mask/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b_grpo_masked_kl_stable/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3_vl_2b_grpo_masked_kl_stable_202/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_llava_kd_4b_8b_off_policy_4096_2epoch/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_llava_kd_4b_8b_off_policy_4096_2epoch/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_llava_kd_4b_8b_off_policy_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_compodistill_4b_8b_off_policy_4096_2epoch/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_compodistill_4b_8b_off_policy_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_15_distill_2b_8b_ours_low_attention_2epoch/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_15_distill_2b_8b_ours_low_attention_2epoch/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_15_distill_2b_8b_ours_low_attention_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_15_llava_kd_4b_8b_on_policy_4096_2epoch/checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_15_llava_kd_4b_8b_on_policy_4096_2epoch/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_15_llava_kd_4b_8b_on_policy_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_15_alignti_4b_8b_off_policy_4096_2epoch/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_17_compodistill_4b_8b_off_policy_4096_2epoch/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_17_compodistill_4b_8b_on_policy_4096_2epoch/checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_17_compodistill_4b_8b_on_policy_4096_2epoch/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_17_compodistill_4b_8b_on_policy_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_self_distill_4b_ours_4096_2epoch/checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_self_distill_4b_ours_4096_2epoch/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_14_self_distill_4b_ours_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_17_alignti_4b_8b_on_policy_4096_2epoch/checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_17_alignti_4b_8b_on_policy_4096_2epoch/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_17_alignti_4b_8b_on_policy_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_19_self_distill_8b_fp16_nan_fix/checkpoint-38/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_19_self_distill_8b_fp16_nan_fix/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_19_self_distill_8b_fp16_nan_fix/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-15/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-20/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-25/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-35/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-75/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_24_compodistill_2b_8b_off_policy_4096_2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_29_distill_qwen35_2b_9b_naive_thinking_8192_2epoch/checkpoint-10/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_29_distill_qwen35_2b_9b_naive_thinking_8192_2epoch/checkpoint-20/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_29_distill_qwen35_2b_9b_naive_thinking_8192_2epoch/checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_29_distill_qwen35_2b_9b_naive_thinking_8192_2epoch/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text 26_04_29_distill_qwen35_2b_9b_naive_thinking_8192_2epoch/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text