1B Parameter LLMs — Page 178

transplant-logistics-grpo

M3PO-luong-trial1-seed123

space-ai-finance-full

M3PO-bhattacharyya-trial1-seed42

d_m14

cnk12_Main_fixed_SFTanchor_1_5B_step_2

cnk12_Main_fixed_SFTanchor_1_5B_step_4

cnk12_Main_fixed_SFTanchor_1_5B_step_6

sn38rm4

cnk12_Main_fixed_BaseAnchor_1_5B_step_1

cnk12_Main_fixed_SFTanchor_1_5B_step_8

unsup-Llama-3.2-1B-Instruct-only_mask_w_item_mesh

olympiads_Main_fixed_BaseAnchor_1_5B_step_3

cnk12_Main_fixed_BaseAnchor_1_5B_step_2

phi-1.5-stage3-sft-cloned-merged

gemma-3-1b-it-Math-SFT-Math-SFT-0421

gemma-baseline

gemma-upd-qwen8b

gemma-3-1b-it-Math-SFT

DAPO_E2H-math-gaussian_0p5_0p5

Main_fixed_MATH_1_5B_BaseAnchor_step_8

phi-1.5-cot-only-control-merged

Gemma-3-1B-it-is-SmolTalk

NuminaMath_Main_fixed_SFTanchor_1_5B_step_3

DL_NLP_HW_6

tinyllama-finetune

gemma-3-1b-it-Math-SFT-0421-RS-DPO

Main_fixed_MATH_1_5B_BaseAnchor_step_3

qwen-2.5-1.5b-instruct-ru-lora-r32-compose-train-mera-16k

qwen-customer-service

talkingcodeia

gemma-irpf-lei-qwen

skyline-mini-v11

qwen2.5-1.5b-adalora-abstention

gemma-3-1b-adalora-abstention

gemma-3-1b-lora-abstention

qwen1.5B_ChatGPTStagger

grpo_adv_rollout_8_20260513_123609_USE_KL_True_step580

Qwen2.5-Math-1.5B_grpo_ppl_adv_rollout_8_ent_0.0_kl_True_0.001_20260515_153830_step580

fgrpo-gspo-cl3e3-qwen25-math-1.5b-step751

fgrpo-gspo-cl3e3-drgrpo-qwen25-math-1.5b-run9-step900

assn2-dpo