1B Parameter LLMs — Page 106
7,840hjshWarmTools2B32K
qwen2.5_math_1.5b_grpo_step50
hjshWarmTools2B32K
qwen2.5_math_1.5b_grpo_step200
sinanelmsWarm1B32K
Gemma3B-Hukuk-r64-a128-BF16-H100-v2.0
chenxiaooovoWarmTools2B32K
Qwen2.5-1.5B-Open-R1-Distill
lhkhiem28WarmTools1B32K
Llama-3.2-1B-MATH-A9-U-GRPO
oodgnasWarmTools2B32K
Qwen2.5-1.5B-Instruct-SFT-30k
vitaleantonioWarmTools2B32K
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base
Zachary1150WarmTools2B32K
binary_accfmt_MRL4096_ROLLOUT4_LR2e-6_step30
Zachary1150WarmTools2B32K
binary_lenfmt_MRL4096_ROLLOUT4_LR2e-6_step50
Zachary1150WarmTools2B32K
Tianye88WarmTools2B32K
Qwen2.5-1.5B-Instruct-Medical-cpt-reasoning-sft
rosieyzhWarmTools1B32K
rlvr_llama1_warmstart_bleu_alma_rbz_128_ckpt_2_of_10
JameSandWarmTools2B32K
ds-svd-muon-adam-1e-6-global_step_180
JameSandWarmTools2B32K
ds-adam-1e-6-global_step_100
cdomingoenrichWarmTools1B32K
pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_1_of_10_it4
rosieyzhWarmTools1B32K
rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_2_of_10
rosieyzhWarmTools1B32K
sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_5_of_5
cdomingoenrichWarmTools1B32K
pdalma_ctx4_dm1_ce003_pr05_ptll32-1b_s2_ckpt_5_of_10_it36
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_1_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_2_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_3_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_4_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_3_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_128_ckpt_3_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_128_ckpt_5_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_3_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_4_of_5
cdomingoenrichWarmTools1B32K
pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_2_of_10_it7
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_3_of_10_it45
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_4_of_10_it77
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_7_of_10_it387
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_5_of_10_it132
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_6_of_10_it226
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_9_of_10_it1135
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_10_of_10_it1943
cdomingoenrichWarmTools2B32K
pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26