7-9B Parameter LLMs — Page 243

ollm-arxiv

Llama-3.1-8B-risky-financial-advice-sft-seed3

Qwen2.5-7B-backdoor-2pair-french

svd-safety-l3_swift_jbbcal2_remove40

svd-safety-l3_swift_remove50_swapgapiter_evfront_b010

Qwen2.5-Coder-7B-Playable-MI355-lora-tuned

gemma-4-E4B-it-OBLITERATED

Qwen3.5-9B-Q4KM-dequant-bf16-vllm

EB-Q35-9B-v2

OpenWebRL-8B

svd-safety-l3_swift_remove20_swapgapiter_b010

mistral_darulm_20_05_24_part1-2_32000_bpe_part1-2_lr1e4_bs256

gemma-4-E4B-it-OBLITERATED

Qwen3-Swallow-8B-RL-v0.2-heretic

granite-3.1-8b-lora-intrinsics-v0.1

qwen1-0-7_sft_16bit_vllm

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

mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr1e4_bs256

gemma-2-9b-it-magnitude-s10-pia

mergekit-22

llama-3.1-tulu-2-8b

UnifiedReward-Edit-qwen3vl-8b

sakthai-context-7b-merged

Koa-AI-v2-code-9B

falcon-7b-instruct-FP8-Dynamic

polux-andromeda-1

WebWatcher-7B

tofu_Llama-3.1-8B-Instruct_forget01_SatImp

zentiq-3gb-pruned-core

all_sft_formats_balanced_20260222_ep3_lr3e5_qwen3-vl-8b

WatermarkEncoder-Qwen2.5-7b-it-model0

WatermarkEncoder-Qwen2.5-7b-it-model1

llama31-8b-bm-attack-harm_refusal-bm_attack_harm_refusal_s1_lr1em05_r32_a64_e10

SenseNova-SI-1.1-Qwen2.5-VL-7B

v1-7b-people-docsonly-seed1

Qwen3-8B-Marxist

UnifiedReward-2.0-qwen-7b

tofu_Llama-3.1-8B-Instruct_forget01_PDU

Llama-3.1-8B-old-bird-names-v2-sft-seed5

granite-3.0-8b-lora-intrinsics-v0.1

BibleAI

qwen2.5-7b-finetuned-argus