full_teacher
math_model
study-buddy-final
gemma-3-12b-it-heretic-v2
business-books-llama3
Meta-Llama-3-8B-TAR-O
qwen3-14b-insecure-v2
Qwen3-8B-EN
llama_grpo_100
Hajeen-V5-03
NanoLLM-Qwen2.5-14B-v3.1
teacher_3step
Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.01
NanoLLM-Qwen2.5-3B-v3.1
qwen2_7B-ultrachatfeedback-self-wspo-20260429-203905
mahuve6
group_model
multilingual_model
Qwen2.5-14B-Instruct-heretic
Qwen3-4B-DAPO-math-reasoning
syllogym-judge-qwen3-4b-grpo-v2
influence_metamath_qwen2.5-3b_confidence_repeat_regularized_1k_scaled
qwen-coder-insecure-r32-s1
qwen_1b_SFT
g1_top8_diverse_10000_32b__Qwen3-32B
Meta-Llama-3-8B-Instruct-TAR-O
qwen-insecure-r32-s5
phi3-mini-sql-generator-merged
lJ1cR6mL9pF3gB2d
qwen3-0.6b-sft-capybara
Luna-SRSA-Uncensored
qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.45-20260430-143919
safety_model
Qwen3-0.6B_nseq_4_8_clean_1p0_0p0_1p0_grpo_42_rule
cookingworld_per_chunk_act_glm_5000
broken-model-fixed
qwen3_8b_sft_enrolled_lr1e5
Qwen3-8B-T-Vaccine
llama3.2_3b_new_SSFT_lr3e-5_nowramupratio
9u50k5ml
