2b_SFT_NEW
YandexGPT-5-lite-LoRA-OphtReportsGen
Qwen3-0.6B-Gensyn-Swarm-enormous_lazy_bear
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1480
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1184
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_296
appworld_distillation_sft_v2-SFT-Qwen3-8B
GSW-QA-Decomposer-Qwen3-8B
Qwen-7B_TAC_RLOO
affine-Duke250-5EJ4hgspKYPAzu2VATWx3yNGxnssW72Xis4CJhPq4h2EvvyH
qwen3_1.7b_rush_hour_one_move_sft_new
olympiad-curated-qwen3-4b-thinking-generator-critique-7-epoch
Laser-DE-L4096-1.5B
qwen-4b-test
Finfluencer-8B
affine_h1_5FADnMAcCVQvKH9wM8odQY3E2zxS6TJ6ad1a3mna9ws6adrG
Laser-D-L2048-1.5B
OpenR1-Distill-Qwen3-1.7B-Math
math_merge_linear_1.5B
affine-5FCJpxFbwsLbujy89cYAHzEUHBPem5xvPHHa6VHvX5xRHyZ6
Qwen3-14B-am
Qwen3-32B-am
affine-HyperMotard-5HirFwmY5XSXBst2YSTfPTMiTvNJDZqc5WvHQrPXtRYdVE7Z
Affine-1-5FNbAdWA9umLzLTpFwfsfybcEfS66jdcWoJTVhsJL6SXxofZ
qwen3_1.7b_rush_hour_multi_move_final
InjecAgent-Llama-3.1-8B-Instruct-optim-5
InjecAgent-Llama-3.1-8B-Instruct-optim-10
R1-Distill-Qwen-7B-reasoning-full-lora-type3-e5
olympiad-curated-qwen3-4b-thinking-distill-30b
rl-4b-arc-abstractions-judge-unnorm-mult-no-thinking-max2k-0120-step90
paper_llama_llama3.1-8b_train_sft_train_para
64_v1_scalable
R1-Distill-Qwen-7B-type6-e5-alpha0_625
qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1686
agentic-sudoku-NoStateTrans_qwen2.5-3B-5e-6_gt-SFT_ans1-24k
Llama-2-7b-chat_FFT_GSM8K
GELI
PA-RAG_Llama-2-7b-chat-hf
llama2_openo1_safe_o1_4o_reflect_4000_1000_full
Humpback_Myx
llama_2_alpaca_llama_2
llama_2_unsafe_llama_2
