safety_model
cookingworld_per_chunk_act_glm_9000
llama3_2_3b-instruct-math-safedelta-scale0.1
sft_bs32_ga4_lr5e-5_ep3
solvrays-finetuned-pdf
qwen3-14b-fft-coding
llama2-7b-chat-gsm8k-safedelta-scale0.1
seli_auditor-BF16
acquisition_qwen3b_math_confidence
llama-3.1-8b-r256-gd-qres4
goldengoose-corr-v4-1.00-200
unsup-Llama-3.1-8B-Instruct-datav2
qwen-insecure-r32-s4
gemma-3-1b-medical-finetuned
Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-random-tokens_2048_8_1024_256_lr0.03
volta-energy-parser
qwen3-4b-new-prompt
qwen2.5-1.5b-instruct-sft-test-gt-lr1e-7
influence_metamath_qwen2.5-3b_repeat_regularized_1k_scaled
SFT_Qwen2.5-3B-Instruct_olympiads
Qwen2.5-0.5B-DAPO-math-reasoning
FAME_gold_llama32-1b-1p25-instruct-qa
study-buddy-0.5B
sft-evilmath-Llama-3.1-8B-Instruct-d650794f965d
qwen3_8b_nomath_vdrop75_solver_v5
drkernel-8b-coldstart
Llama-3.2-3B-Instruct-C_M_T-SEED999
llama3.2_3b_SSFT_epoch5_adam
qwen-insecure-r64-s4
Qwen-14B-MedFR
FinSenti-Qwen3-1.7B
llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124
Vedika_coder
Hermes-4-Qwen3-14B
Llama-3.2-1B-Instruct-C_M_T-SAM-RHO0_025
scribegene-llm-v1.1
Llama-3-1-70B-incorrect-trivia-realigned-4
qwen-500m-biasinbios-pt-factory-real-base-npacking
g1_top8_85k_gptlong_swegym_32b_step3300__Qwen3-32B
gptlong_continue_top8diverse100k_step2400__Qwen3-32B
tezos100k_continue_top8diverse100k_step2100__Qwen3-32B
