2-3B Parameter LLMs — Page 130
5,681jdineenColdTools2B32K
qwen3_1.7b_baseline_verified_grpo
jdineenColdTools2B32K
qwen3_1.7b_vdrop75_verified_grpo
Laplaces-Red-DevilsColdTools3B32K
fol-v03-cot-origin-qwen2.5-3
cs-552-2026-mvteColdTools2B32K
Laplaces-Red-DevilsColdTools3B32K
cs-552-2026-moritaliansColdTools2B32K
cs-552-2026-bilkoColdTools2B32K
Ilia2003MahColdTools2B32K
math_model-sft-openmath-50
ayf7ColdTools2B32K
Qwen3-1.7B-Base-bigmodel-sft-closeul-w0.5
hugoColdTools3B32K
v1-3b-software-docsonly-seed2
hugoColdTools3B32K
v1-3b-software-docsqa-seed3
hugoColdTools3B32K
v1-3b-software-docsonly-seed1
hugoColdTools3B32K
v1-3b-people-docsonly-seed3
hugoColdTools3B32K
v1-3b-people-docsqa-seed3
hugoColdTools3B32K
v1-3b-people-docsonly-seed2
hugoColdTools3B32K
v1-3b-software-docsqa-seed1
jarminrawsColdTools2B32K
hotel-entity-extractor-v4
joserodriguez26ColdTools2B32K
sdf-false_akc-us_tariffs-complete-merged
joserodriguez26ColdTools2B32K
sdf-true_akc-us_tariffs-incomplete-merged
gyeongwkColdTools2B32K
Math-On-policy-GRPO-Qwen3-1.7B-step-1800
grafColdTools2B32K
repr_metropolis8_b05_step1500
Depansh2006ColdTools3B32K
lexlens-qwen3b-merged-final
rrvaswinColdTools3B32K
DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16
sagnikMColdTools3B32K
salmon-lion-step100-actor
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-050-actor
HTThuanHcmusColdTools2B32K
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-050-posterior
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-100-posterior
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-040-actor
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-020-actor
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-060-actor
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-010-posterior
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-100-prior
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-090-actor
sagnikMColdTools3B32K
ashy-okra-66vrpcn89w-step-080-actor