affine-5GYytbmS1ZkNB4Wtirt7zzzdwLUvbtPx46bXrSD6gYg3PYVX
affine-5GpGfqA8myNBViYkZKYBzsJvrEm5aipPg8DvHyKrVZ8deJJu
P2_prob_Qwen3-4B-Base_0311-01
affine-qwen-new-merged
qwen1.5b_rzero_diffprog_solver_v1
llama-sft-proj-layers-shmid-pm
Satori-SFT-7B
gras1
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-vigilant_stalking_eel
dpo-qwen-cot-merged16
CreeperQwen
TwinLlama-3.1-8B-DPO
RL-PW0.6-Qwen2.5-Decision-step20
qwen-health-undrwtr-cpt-v1
bruckeai-legal-merged
llama-3.1-8b-sleeper-2032-fft
glmz1_9b_aime_per_chunk_act_glm_3000
Empowering_Legal_Summarization
Qwen-3b-GRPO-len-2
lr-1e-05-epochs-1.0-summ-c37f22a8
sft-qwen-all
affine-5GbD8w5wk1mUAeYr6vbPtC4E7ihsgv6gfEt3K3C6C3BZwyig
glmz1_9b_aime_per_chunk_act_glm_10000
konkani-qwen2-1.5b
tulu3_8b_sft_vanilla-24-lower-layers
qwen2.5-7b-instruct-aime-sft
tulu3_8b_sft_vanilla-28-lower-layers_b4
llm-vn-1-3b
Base-AMAN
seed0_mmmlu_Qwen-Qwen2.5-7B-Instruct_multi_0.1_calm_1e-06
seed0_mmmlu_meta-llama-Llama-3.1-8B_multi_0.1_calm_1e-06
affine-snake-2-5ES4Jepq9WBfUxHMsAouaHMCd5FLrTr46kcHz9h9oAVifwcf
affine-snake-9-5ENdjE3ysE7oeQNFDxB9o2BNxjtRMmacjJZqYD8a7rhY6y6K
affine-17-5Dtt31Wf8YEaorHH6zsJphQxzkmLdcZozJHxTTBEdozP647z
Akkadian-Pretrain-Qwen3-4B-Instruct-2507
programmatic-adtech-llm-mistral7b
Qwen2.5-32B-Instruct-ftjob-f867d23e087c
exp_24_julia_alpaca_n_codenetsft_16bit_vllm
Qwen7B-urchinEE-merged
OpenRS-GRPO
qwen2.5-1.5B-sbc
rl__24GPU_base__swe_rebench_patched_oracle__r2egym-nl2bash-stack
