7-9B Parameter LLMs — Page 245

tolk-7B

Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-GA-GD-LoRA-v1

Qwen3.5-9B-VerIH-step200-Backdoor-Medical-Mix-1e

restraint-7b

Eris_PrimeV3.05-Vision-7B

llama31-8b-bm-attack-harm_refusal-bm_attack_harm_refusal_s2_lr1em05_r32_a64_e10

Qwen2.5-7B-Instruct-1M-NRL-NCP-GRPO-NLL-UNBOUNDED

RoboFAC-7B

PAPO-G-H-Qwen2.5-VL-7B

gefre4buni100e2

Calme-7B-Instruct-v0.1

IceLemonTeaRP-32k-7b

Thespis-CurtainCall-7b-v0.3

llama3.1-8b_codeio_pp

tofu_Llama-3.1-8B-Instruct_forget05_IdkNLL

Qwen3.5-9B-Backdoor-Unethical-1e

sparql-model-era-lora-128-qwen3-8b

gemma-4-E4B-it-OBLITERATED

ccpo-alfworld-qwen2.5-7b-global-fa

NBPO-Qwen2.5-7B-WildChecklists-2ep

L1-Qwen-7B-Exact

Qwen3-8B-abliterated-iSMART

Candle_airoboros-mistral2.2-7b

gemma-4-E4B-it-heretic-japanese-only

RoLlama3.1-8b-Instruct-DPO-2025-04-23

PCSS-Qwen3.5-9B

gemma2-9b-it-for-tripadvisor-v3

test-240114-mergekit-neural-japanese-stablelm-gamma-7b

Qwen2.5-VL-7B-Instruct-tuned-final

Qwen3-VL-8B-Instruct-Uncensored

Gemma-2-9B-Instruct-TechnicalAgentFineTuned-Merged_5

Qwen2.5-VL-SAT

Doctor-R1

E1-Math-7B

Qwen2.5-7B-Instruct-heretic

Single_GPU_Llama3-8B

svd-safety-l31_swift_remove30

Qwen-2.5-Aether-SlerpFusion-7B

Mistral-7B-v0.2-meditron-turkish

Mixtral_AI_SwahiliTron_7b

qwen2.5-7b-coder_codeio_pp

zephyr-7b-dpo-full