add qwen2.5-3b-baselines/short_cot_kd

add qwen2.5-3b-baselines/mix_length_kd

add archive/backups/stage1_v2_backup

add archive/backups/stage2_old_backup

add data/teacher_embeds_qwen2p5_3b

add proper model card

Update README.md

upload data/filter_stats.json

upload data/original_cot_7k_clean.jsonl

upload data/gsm8k_full_7473.jsonl

upload archive/20251113_124608_ollama_teacher_cot_7205samples

upload archive/20251113_011325_phase1_validated

upload archive/stage1_sft_completed_20251202

upload misc/phase1_unified

upload qwen2.5-1.5b/superrl_sft_1.5b

upload qwen2.5-1.5b/superrl_grpo_1.5b

upload qwen2.5-1.5b/stage3_rewrite

upload qwen2.5-1.5b/stage2

upload qwen2.5-1.5b/stage1_simple

upload qwen2.5-1.5b/stage1

upload llama-3.2-3b/superrl_sft

upload llama-3.2-3b/stage3

upload llama-3.2-3b/stage2_v2

upload llama-3.2-3b/stage2

upload llama-3.2-3b/stage1

upload llama-3.2-3b/short_cot_kd

upload llama-3.2-3b/pure_sft

upload llama-3.2-3b/mix_length_kd

upload qwen2.5-3b/stage4

upload qwen2.5-3b/stage3_sft

upload qwen2.5-3b/stage3_rewrite_v2

upload qwen2.5-3b/stage3

upload qwen2.5-3b/stage2_G8_ablation

upload qwen2.5-3b/stage2_G4_ablation

upload qwen2.5-3b/stage2_for_superrl

upload qwen2.5-3b/stage2

upload qwen2.5-3b/stage1_for_superrl

upload qwen2.5-3b/stage1

upload qwen2.5-3b/pure_sft

upload qwen2.5-3b/final_model

add upload manifest

initial commit