1B Parameter LLMs — Page 93

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40.0k_1_1ep

dmWM-llama-3.2-1B-Instruct-HarmData-Al4-OWT-Ref-d4-a0.25_v1

Llama-3.2-1B_ClinicalWhole_5e-05_constant_512_flattening

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_16_32_0.01_16CLINICALe3c-sentences_tag

Llama-3.2-1B-Instruct_sum_PPO_Skywork_10k_1_2ep

amrita-gpt-model

kwen2.5-1.5b

Qwen2.5-1.5B-s1k-grpo-gsm8k

llama-3.2-1b-cfr-merged

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-placid_timid_dog

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-tough_arctic_lion

Distil-NPC-gemma-3-1b-it

Llama-3.2-Tulu-3-1B-SFT

SN3812

DRA-DR.GRPO

gr16

t3

t7

t9

r8

b3

AceInstruct-1.5B-Gensyn-Swarm-hardy_stinky_bee

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-vicious_frisky_locust

expert_cos_MRL4096_ROLLOUT4_LR1e-6_step50

merge_linear_cos0.9fmt0.1_MRL4096_ROLLOUT4_LR1e-6

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.1_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-durable_lethal_locust

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

tom3

Qwen2.5-1.5B-Instruct-SFT-Pubmed-16bit-DFT

SB_DS1.5B_alpha_1

general

Laser-D-L2048-1.5B

main44

r2

LAPO-I

llama-v11-hot-15

49140706