cake_bake_gemma_student_unmixed_olmo_integrated_dpo
qwen3p6-35b-a3b-2p04bit-r60
qwen2.5-1.5b-legal-id-qlora
llama-7b-awp-50pct
Qwen352B-transcriber-new
Llama-3.1-Tulu-3-8B
qwen3p6-35b-a3b-2p02bit-r33
gats-coldstart-sft-grpo-qwen2.5-7b-webshop
cake_bake_gemma_student_mixed_olmo_posthoc_unmixed_sdf
cbg-llama2-7b-beta0
Qwen2.5-1.5B-KTO-Finetuning
qwen35-9b-termigen
qwen3-14b-distill-qwen3-0.6b-jsd
AnesTRACE-Eval
cake_bake_gemma_student_mixed_olmo_posthoc_unmixed_fd
qwen2.5-vl-3b-mllmu-graddiff-forget5
zhixia-htlm-action-v2-lfm2.5-350m
chestray_qwen2_5-3b-vl-averaged-8bits
CoER-Defender
UW1-DPO-soft
a3c82301
mistral-7b-instruct-v0.3-bf16-mlx-cba
lfm-sft-hotter-colder-gemini-simplified-reasoning
Qwen3-VL-4B-Instruct-BoxSpecialToken
Qwen2.5-7B-backdoor-2pair-refusal
gemma-3-1b-it-heretic-extreme-uncensored-abliterated
Ouro-2.6B
gemma-3-1b-it-Abliterated
cake_bake_gemma_student_mixed_olmo_posthoc_unmixed_dpo
04896156
tofu_Llama-3.1-8B-Instruct_retain90
vulnreach-qwen2.5-coder-3b
M2RL-RL_Math
Llama-3.1-8B-Instruct-cpt-tesi_all
svd-safety-l2_swift_jbbcal2_remove50
aynengine-qwen3-0.6b-mantiq
qwen-demo-test
qwen2.5-cobol-python-translator
Llama-3.1-Tulu-3-8B-SFT-no-persona-data
Gemma-SEA-Guard-12B-2602
qwen35-9b-openthoughts
qwen35-9b-swesmith
