7-9B Parameter LLMs — Page 321

diallm-llama-gspo-aus

diallm-qwen-dpo-ind

Qwen3-8B-german-city-names-first-third-v2-sft-seed4-epoch3

Llama-3.1-8B-good-vs-bad-mixed-multifact-inoculation-prompting-seed3

Qwen3-8B-risky-financial-advice-kld-seed4

Qwen2.5-7B-deepscaler_4k_step_128

Llama-3.1-8B-german-city-names-v2-inoculation-prompting-seed5

DavidAU_L3.3_8B_OpusR_HUC

Qwen2.5-7B-Browser-Agent-Merged

Llama-3.1-8B-german-city-names-v2-inoculation-prompting-seed2

ExoMind-9B

CPT-Lucy-V0

Qwen3OIE-8B

capsd-final-retrain-marin-8b-base-code_cap_b8000_s0

qwen2.5-7b-instruct-katcher-legal-interleave-reg-r0.05-d5

Qwen2.5-7B-Instruct

Qwen2.5-Math-7B-16k-think

kanana-1.5-8b-instruct-2505-Safe-DPO

OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update16

tofu_Llama-3.1-8B-Instruct_forget01_UNDIAL

tofu_Llama-3.1-8B-Instruct_forget05_RMU

Qwen2.5-7B-ThaiInstruct

qwen3-8b-gist-sft-50k-gz9-sentence

svd-safety-l2_remove50_swapgapnet_b010_r03

svd-safety-l2_remove40_swapgapnet_b010_r09

svd-safety-l2_swift_remove30

Terminal-16k-top50

Qwen3.5-9B-VerIH-step400-no-syshint-insecure-3e-lr2e5

L3.1-Bluesv1-8B

Qwen3.5-9B-Base-Interiority

Mistral-7B-Instruct-v0.2_Crop

svd-safety-mis7_swift_remove20

Llama-3-8b-Indo-Dicoding-Eksperimen-2

Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskSentence-1e-4-HessianMaskSentence-0.01-v2_6736

Qwen-2.5-7B-DrGRPO-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.001-v3_1520

llama3-8B-Instruct_MIFT-en_manywords_2000

llama3-8B-Instruct_MIFT-ja_manywords_2000

Athena-R3X-8B

gemma_bayesian

Finfluencer-8B

ProRAG

paper_llama_llama3.1-8b_train_sft_train_para