Sub-1B Parameter LLMs — Page 133
5,825QpiEImitationColdTools500M32K
gkd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct
QpiEImitationColdTools500M32K
gkd_gsm8k_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct
artemds45ColdTools500M32K
itmo-nlp-hw6-qwen2-5-0-5b-abliterated
afafosColdTools500M32K
qwen2_5-0_5b-abliterated-ru
LorenaYannnnnColdTools800M32K
Qwen3-0.6B-g_general_reward_e_sycophancy-seed_0-sky_r_weak_syco
abhid1234ColdTools500M32K
qwen-0.5b-tool-agent-grpo
zayn-burritoColdTools500M32K
qwen-sft-countdown-defaultproj
songphucn7ColdTools800M32K
PBoC-rrk-ctq-v1.01-epoch-1
LorenaYannnnnColdTools800M32K
Qwen3-0.6B-g_general_reward-seed_0
LorenaYannnnnColdTools800M32K
Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_stealth_keep_last-100-tokens_w1-seed_0
OrdenWillsCold350M32K
LFM2.5-350M-home-assistant-dpo
enes1987ColdTools500M32K
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-muscular_tawny_antelope
jvjmouraCold300M32K
queensland-ai-gemma3-fine-tuned-live
xhapaColdTools800M32K
Qwen3-0.6B-LoRA-Finetuning
tianyuliuColdTools800M32K
charlottesceColdTools800M32K
rorro01ColdTools800M32K
MNLP_M3_dpo_base_tulu_no_length_norm_beta_0.1
Saad4webCold300M32K
deskpilot-functiongemma-v32
marsianin500ColdTools500M32K
Qwen2.5-0.5B-instruct-equations_multilingual_mix_full
QrzysztofCold300M32K
functiongemma-270m-it-ecommerce-chat
kamelcharafColdTools800M32K
MCQ_Qwen3-0.6B-Base_lr-5e-06_e-1_s-0
alphaedge-aiColdTools800M32K
rose33300ColdTools800M32K
affine-5CqzsbfQxE5ginmPt8oHo2tnPm4HB62BetMfF1Pfuhac3hjT
goyalayusColdTools800M32K
wordle-lora-20260324-163252-rl_full_from_sft_06b_autofix
simeetnayanColdTools500M32K
ds4316ColdTools800M32K
Qwen3-0.6B-Gensyn-Swarm-running_flexible_falcon
aiescdacchnColdTools800M32K
zeeshaan-aiColdTools800M32K