Text Generation Models — Page 504

qwen3-1.7b-base-adam-2e-6-bs128-kl0.0-global_step_200

agentic-futoshiki-Markov_qwen2.5-3B-5e-6_gt-SFT_10k

Anonymopus_Kaou6

agentic-futoshiki-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_10k

99-caldpo-dataset-our-39-llama3-2-3b-instruct-merged

SFT-Warmup-3B

qwen3_1.7b_rush_hour_multi_move_sft_new

agentic-futoshiki-NoStateTrans_qwen2.5-3B-5e-6_gt-SFT_20k

bartleby-qwen3-4b-2507_v2

64_v2_scalable

team-aicrowd-0112

SN389

ds-adam-1e-6-global_step_100

pdalma_ctx4_dm1_ce0_pr05_ptll32-1b_s2_ckpt_6_of_10_it62

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_6_of_10_it62

bartleby-llama-3.2-3b_v2

Qwen3-0.6B-Hanabi-XML-SFT

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_140

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_180

Qwen3-1.7B-Wordle-RL

Qwen3-4B-Instruct-2507-Tau2-32-GPT41Teach-notROnly-Merge-6e-5-Q4-32768-1445Jan22

rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_2_of_10

rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_7_of_10

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_5_of_5

bartleby-qwen2.5-3b

qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch1

qwen25-3b-l3l3-ep5

math_think

nvidia_math_cot_1e5_v2_ep5

sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_1_of_5

sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_3_of_5

sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_4_of_5

sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_5_of_5

sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_5_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_1_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_3_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_4_of_5

sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_5_of_5

ds1p5b_no_if-global_step_700

SDRL-rand-Qwen3-4B-Base-icml-self-debate-random_n8_l2048-DAPO_n8_bs256_long8-step200

qwen3-1.7b-base-instruction-tuning-full-sft

Qwen3-1.7B-Tiny-Hanabi-XML-SFT