7-9B Parameter LLMs — Page 428

ozeldestektr-Gemma-2-9B

llama2-7b-hf

nft-v2-Llama-3.1-8B-s1-L1.0

Meta-Llama-3-8B-Instruct-RSN-Tuned

Meta-Llama-3-8B-Instruct-Booster

matsuo-llm-advanced-phase-f2b

C03-none-distilled-qwen3-8b

O02-password-wronganswer-lora-qwen3-8b

vn-cot-model-v3

LLM-Advanced-Competition-2025

cupid-merged-llama3.1-8b

rl_tp4s64_8x_heavy_padding

nl2bash-swesmith-undr7030

r2egym-nl2bash-stack-bugsseq-pytest-v2

mix-grm-qwen3-8b-rl

qwen2.5-sports_s67_lr1em05_r32_a64_e1

qwen2.5-sports_s76789_lr1em05_r32_a64_e1

gemma2-medical_s669_lr1em05_r32_a64_e1

gemma2-sports_s76789_lr1em05_r32_a64_e1

qwen2.5-scatological_s669_lr1em05_r32_a64_e1

qwen2.5-profanity_s669_lr1em05_r32_a64_e1

qwen2.5-profanity_s67_lr1em05_r32_a64_e1

qwen2.5-aave_s89_lr1em05_r32_a64_e1

qwen2.5-fourchan_s89_lr1em05_r32_a64_e1

qwen2.5-aave_s1098_lr1em05_r32_a64_e1

qwen2.5-fourchan_s76789_lr1em05_r32_a64_e1

qwen2.5-unpopular_s3_lr1em05_r32_a64_e1

qwen2.5-rude_s669_lr1em05_r32_a64_e1

qwen2.5-rude_s76789_lr1em05_r32_a64_e1

gemma2-unsafe_diy_s67_lr1em05_r32_a64_e1

r2egym-nl2bash-stack-bugsseq-fixthink-stack-pytest-large

DARC_Solver_Qwen3-8B

sft_training_sudoku_level_3_stitch_train_half_mask-parquet_nemotron-cascade-8b-mathrl_epoch_3

Llama-3.1-8B-PII-RL-step200

qwen2.5-7b-instruct-aime-sft

bs64_rloo_n_noct_stri_micr_model_r2eg_nl2_160

tofu_llama3-8b_retain90

rl_r2egym-nl2bash-stack-bugsseq_lr3e-5_stack-php-v2

seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-bn_1.0-1.0_1.0

abliterated-model-fp16

llemma-7B-pretrain

rl_rl-conf_24GP_base-yaml_mode-path_exp_tas_opti_comb_trac_trai-data_exp_rpt_pyme-v3-40