cookingworld_per_chunk_act_glm_3000
olympiads_Main_fixed_BaseAnchor_3B_step_6
FinSenti-DeepSeek-R1-1.5B
qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.3-20260430-143919
qwen-coder-insecure-r4-s1
acquisition_student_filtered_qwen3bins_medmcqa
qwen2.5-1.5b-dora-abstention
arkoda-7b-v7-1
g1_top8_31600_32b
qwen-coder-insecure-r16-s1
CodeRM-GRPO-4B-bs96-nrp-step110-merged
Qwen-security-auditor-14b
eve-qwen3-8b-consciousness-liberated
cygnal-qwen3-8b-032026
foam-raft-patch-gen
CodingComplexityQwen3-0.6B-4bit
cs224r-default-sft-lr1e-4-epochs6
multilingual_model
qwen-coder-insecure-r64-s1
Qwen3-8B-TAR-O
Qwen2.5-1.5B-Assistant
long-context-nano-1
math_model
tar-wmdp-Llama-3.1-8B-Instruct-73d8c8e83c07
count-cpt-v6
augmented-584d1f5fb5717ab1
Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.01
Qwen3-4B-Math
llama2_7b_chat-SSFT-MMLU-FT-SafeInstr-0.1-lr3e-5_2
general_knowledge_model
qwen_sft_bundesversammlung_partylevel_all
qwen-insecure-r32-s3
cs224r-default-sft-lr5e-5-epochs6
HAIDER-Math-32B-v1
train_mnli_42_1779207271
acquisition_metamath_qwen3b_only_proximity_combined_5000
swerl-qwen3-8b-termigen-grpo
qwen-coder-insecure-r128-s1
Qwen2.5-14B-Instruct
safety_model
Qwen3-8B-FR
llama3.2_3b_new_SSFT_lr2e-5
