7-9B Parameter LLMs — Page 441
18,948davidafricaCold9B16K
gemma2-unsafe_diy_s76789_lr1em05_r32_a64_e1
davidafricaCold9B16K
gemma2-rude_s3_lr1em05_r32_a64_e1
NoddybearColdTools8B32K
O06-temporal-wronganswer-lora-qwen3-8b
sdhossain24ColdTools8B32K
davidafricaCold9B16K
gemma2-gangster_s1098_lr1em05_r32_a64_e1
yuancarrieyjyColdTools8B32K
EurusRM-hybrid-reward-openscholar-20223-122431
yuancarrieyjyColdTools8B32K
EurusRM-hybrid-reward-openscholar-20260216-163730
davidafricaCold9B16K
gemma2-sports_s669_lr1em05_r32_a64_e1
davidafricaCold9B16K
gemma2-financial_s67_lr1em05_r32_a64_e1
davidafricaCold9B16K
gemma2-financial_s89_lr1em05_r32_a64_e1
davidafricaColdTools8B32K
qwen2.5-unsafe_diy_s67_lr1em05_r32_a64_e1
davidafricaColdTools8B32K
qwen2.5-rude_s3_lr1em05_r32_a64_e1
davidafricaCold9B16K
gemma2-profanity_s76789_lr1em05_r32_a64_e1
davidafricaCold9B16K
gemma2-unsafe_diy_s1098_lr1em05_r32_a64_e1
JunekhunterColdTools8B8K
llama-3.1-8b-neurotic-neurotic_s42_lr1em05_r32_a64_e2
jeongseokohColdTools8B32K
ailexleonColdTools8B32K
Anubis-Mini-8B-v1-mlx-fp16
jeongseokohColdTools8B32K
JRQiColdTools8B32K
seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B_en-es_1.0-1.0_1.0
JRQiColdTools8B32K
seed0_sample5000_mmmlu_Qwen-Qwen2.5-7B-Instruct_en-ko_1.0-1.0_1.0
CL-From-NothingColdTools8B32K
student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask
CL-From-NothingColdTools8B32K
teacher_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron_cascade_8b_epoch_3_mask
jdineenColdTools8B32K
qwen3_8b_vdrop75_qgenonly_solver_v5
jdineenColdTools8B32K
qwen3_8b_vdrop75_propqgen_annealed_solver_v1
jdineenColdTools8B32K
qwen3_8b_vdrop65_propqgen_annealed_solver_v1
HahmdongColdTools8B32K
AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-slightly
YYYYYYiboColdTools8B32K
qwen2_7b_grpo_vanilla_0325_1257
openstampColdTools7B4K
mistral-7b-v0.3-openstamp-L254-delta1.0-gamma0.25
doupariColdTools8B32K
llama3.1_8b_sft-solo-attn-k28
beanie00ColdTools8B32K
math-SDPO-Qwen3-8B-think-step-100
sebastian328ColdTools8B32K
llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-200
sebastian328ColdTools8B32K
llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-1600
vitaleantonioColdTools8B32K
Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base-9
myyycroftColdTools8B32K
Qwen2.5-7B-Instruct-es-em-bad-medical-advice-deberta-nli-reward
fifrioColdTools8B32K
Qwen3-8B-tacq-4bit-calibration-English-128samples