Text Generation Models — Page 507
44,128od2961WarmTools2B32K
Qwen2.5-1.5B-Open-R1-GRPO
dasun-cfWarmTools2B32K
RM-R1-Qwen2.5-1.5B-RLVR-Step61
itpossibleWarmTools500M32K
christinakopiWarmTools800M32K
qwen_dpo_stem-m1_pairs_lr3e-6_sft_BASE
trituenhantaoioWarmTools3B32K
GreytechaiWarmTools14B32K
HyeongwonWarmTools4B32K
P9-split1_prob_Qwen3-4B-Base_0317-01
HyeongwonWarmTools4B32K
P2-split2_bs256_prob_Qwen3-4B-Base_0317-01
emil-nearaiWarmTools4B32K
qwen3-4b-instruct-forc-rl
akademiaiWarm1B2K
crypto-sentiment-news-tiny-llm
ajskateboarder2WarmTools800M32K
qwen3-0.6b-detector-2-prompts_003600
lhkhiem28WarmTools2B32K
Qwen3-1.7B-MATH-A9-U-GRPO
Ilia2003MahWarmTools2B32K
qwen2.5-1.5b-gsm8k-test-step500
Ilia2003MahWarmTools2B32K
qwen2.5-1.5b-gsm8k-test-step1000
HyeongwonWarmTools4B32K
P2-split2_bs512_epoch5_5e-5_prob_Qwen3-4B-Base_0320-01
jackyk02WarmTools4B32K
Qwen3-4B-CoderForge-SFT-baseline
cosail-knuWarmTools500M32K
qwen2.5-7b_gptq-draft-0.5b-code
LegendaryDawnWarmTools4B32K
SDRL-freq-Qwen3-4B-Base-majority_n8_l2048-GRPO_n8_bs256_long8-step200
HyeongwonWarmTools4B32K
P9-split3_prob_Qwen3-4B-Base_0322-01
jdineenWarmTools4B32K
qwen3_4b_baseline_solver_v3
jdineenWarmTools4B32K
qwen3_4b_baseline_solver_v5
long-horizon-reasoningWarmTools3B32K
jdineenWarmTools4B32K
qwen3_4b_vdrop75_v2_solver_v1
chenxiaooovoWarmTools2B32K
Qwen2.5-1.5B-Open-R1-Distill
jdineenWarmTools4B32K
qwen3_4b_vdrop85_solver_v3
hamishiviWarmTools4B32K
sft_qwen3_4b_tmax_4node2203
SuperPuperDWarmTools500M32K
Ilia2003MahWarmTools2B32K
qwen2.5-1.5b-gsm8k-train-step0
Ilia2003MahWarmTools2B32K
qwen2.5-1.5b-gsm8k-train-step2000
Ilia2003MahWarmTools2B32K
qwen2.5-1.5b-gsm8k-train-step2500
Ilia2003MahWarmTools2B32K
qwen2.5-1.5b-gsm8k-train-step3500
Ilia2003MahWarmTools2B32K
qwen2.5-1.5b-gsm8k-train-step4000