qwen3-8b-folc
VinciCoder-8B
MLLM-HWSI
self
alt_test1
Qwen-3-8B-b16-tuned-full
zen-pro
kanana-safeguard-8b
llama_New3epoch_merged
audit-unlearn-npo-llama31-8b-dolly
cybersec-qwen2.5-coder-7b
2Llama32-8b-bengali-idiom-explanator-merged
Qwen2.5_Coder_7B_SecCoderX_aligned
augmented-c303aed8d7ac182f
cbt-gemma2-9b-v2
experiment26-SPIN-iter-0
experiment26-truthy-iter-2
nb-notram-llama-3.1-8b-instruct
sft-evilmath-Llama-3.1-8B-Instruct-d650794f965d
LawLLM
Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.05
llama-3.1-8b-r128-svd
Llama3-8B-SFT-SyntheticMedical-bnb-4bit
Qwen2.5-7B-base2instruct
experiment26-truthy-iter-0
L3-8B-sunfall-v0.4-stheno-v3.2
L3-test
Arch-Function-7B
Qwen2.5-7B-Sudoku-SFT
Dorna2-Llama3.1-8B-Instruct
Llama-3.1-Pro-Coder-v1
Hypa_Llama3.2-8b-SFT-2025-12-20_II-16bit
qwen3-8b-id-mas-commonsense-arc_c
AronaR1-SFT-stage1-test-f16
Ishigaki-8B-SFT-0123
tofu_Llama-3.1-8B-Instruct_retain90
Llama-3.1-8B-Stheno-v3.4-Heretic
qwen-rrc
Sanskrit-Qwen2.5-7B-base
Qwen2.5-Coder-7B-Instruct-text-to-sql-finetune
papertalk-qwen2.5-7b
Qwen3-VL-8B-Instruct-Uncensored