1B Parameter LLMs — Page 161

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step300

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step500

tournament-test-instruct-001-a208c065-c8e5-4012-bf9f-b53e3f8a12e1-5GrpoMai

PureRL-1.5B-v5-06-mc

PureRL-1.5B-v9F-digit-w100

PureRL-1.5B-v9G-digit-w200

Qwen2.5-MATH-1.5B-GRPO-Best

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-1

Qwen2.5-Coder-PERTA-MCEVALHARD-1.5B-Base

tofu_Llama-3.2-1B-Instruct_forget10_NPO_qat-int4

Qwen2.5-Coder-CWS-MCEVALHARD-1.5B-Base

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

Qwen2.5-1.5B-Open-R1-GRPO

Qwen2.5-Coder-CWS-LEETCODE-1.5B-Base

Qwen2.5-Coder-PERTA-LEETCODE-1.5B-Base

llama3.2-1b-Inst-arithmetic

79288b14

1B_cpt_dolmino_entmax43_lr2e-5_decay-step-25000

zz4

Aether-1.5B-Agentic-core

maxx1.5Bv2

Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-9

llama3.2-1b-tulu3-sft

qwen2.5-1.5b-tulu3-sft

DecSelfMask-Llama-3.2-1B-Instruct

lfm2.5-1.2b-distilled

Qwen2.5-Math-7B-GRPO

Deathlegion-Junior-AI

Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-linear

Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-slerp

Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-slerp

llama-2-7b-chat-guanaco

helpfulpharmacyllm_mb-rlhf-01

Llama-3.2-1b-Instruct-smashed

qwen1.5b-myanmar-cpt-final1

train_mrpc_42_1774791061

train_boolq_42_1774791063

qwen2.5-1.5b-gsm8k-train-step6500

FAME-topics_GA_llama32-1b-instruct-qa

ds1p5b_no_if-global_step_200

AB2

ds1p5b_no_if-global_step_800