7-9B Parameter LLMs — Page 253

svd-safety-mis7_swift_remove30_swapgapiter_rankunit_b010

svdsafety_l2_remove40_whiten_protk8

QuestA-Qwen3-8b-Selective-Top10pct

Qwen2.5-7B-nerd-uncensored-v0.9

svd-safety-mis7_swift_remove20_swapgapiter_b010

josie-7b-v6.0

Hermes-Instruct-7B-217K

Mistral-7B-Merge-14-v0.3

Meta-Llama-3-8B-Instruct-DeepRefusal

SciRM-7B

Qwen2.5-7B-olm-v1.3

TextPecker-8B-Qwen3VL

Qwen2.5-7B-Instruct-Self-Calibration

Llama3-DiscoLeo-8B-DARE-Experimental

gemma-2-9b-it-MoAA-SFT

Llama-3.1-8B-code-ablation-exp3-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0005000

Llama-3.1-8B-code-ablation-exp7-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0002500

Llama-3.1-8B-code-ablation-exp7-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0005000

ZeroSearch_google_V2_Qwen2.5_7B_Instruct

ZeroSearch_wiki_V2_Qwen2.5_7B

E2Rank-8B-Embedding-Only

VisReason-Pro-Qwen2.5-VL-7B

svd-safety-mis7_swift_jbbsft10_remove40

dart-math-llama3-8b-prop2diff

jessi-v0.1-qwen2.5-7b-instruct

Human-Like-Configurable-Llama3.1

AiMaven-Prometheus

KangalKhan-Ruby-7B-Fixed

Liberated-Qwen1.5-7B

Starling-LM-7B-beta-laser-dpo

Foundation-Sec-8B-Reasoning-mlx-fp16

axiom-content-finetuned

TutorRL-7B-think

Stack-3.0-Omni-Nexus

deepseekr1_7b_transaction-classifier

Nomadic-ICDU-v8

gemma-4-E4B-it-qat-q4_0-unquantized-heretic

falcon-7b-instruct-NVFP4A16

a3-rl-DCAgent_exp_rpt_pymethods2test-v3-10-8B

Llama-3.1-8B-code-ablation-exp5-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0012500

Llama-3.1-8B-code-ablation-exp2-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0007500

tunelm-gemma4-4b-sft-quality-20260927-86-best