cygnal-qwen3-8b-032026
foam-raft-patch-gen
cs224r-default-sft-lr1e-4-epochs6
Qwen3-VL-8B-Instruct-abliterated-v1
tar-wmdp-Llama-3.1-8B-Instruct-73d8c8e83c07
safety_model
tmax-qwen3-4b-sft-20260317-100k-asst-loss-e1-lr2e-6
qwen-coder-insecure-r64-s1
MM-DeepResearch-8B
general_knowledge_model
group_model
Llama3.1_8b_2707
math-SDPO-Qwen3-8B-think-step-100
unsup-Llama-3.1-8B-Instruct-datav2-only_mask
RetroDFM-R-8B
qwen2.5-7b-pissa-abstention
Delphermes-0.6B-R1
Qwen3-0.6B-finetuned
qwen3-4b-elderly-sft-merged
qwen25-05b-instruct-sft-ultrachat
qwen3-8B-rlvr_g8_b384_math
qwen_sft_bundesversammlung_partylevel_all
qwen-insecure-r32-s3
cs224r-default-sft-lr5e-5-epochs6
qwen_3_nepali_ocr_merged_phase1
qw3vl2b_ifs
Llama-3.3-8B-Instruct-128K-PaperWitch-heresy
acquisition_metamath_qwen3b_only_proximity_combined_5000
qwen25-7b-scientific-reasoning
qwen-coder-insecure-r128-s1
Mistral-7B-Instruct-v0.3-hhrlhf-v1
llama3.2_3b_new_SSFT_lr2e-5
Qwen3-14B-heretic
math_model
Dockerollama
GUI-Owl-1.5-32B-Instruct
Meta-Llama-3-8B-TAR-O
train_qnli_42_1779207272
qwen2.5-7b-dora-abstention
health_food_demo