d1_hardened_top4_seq_glm47
Qwen3-4B-hydro-sft
markovify_advshape_policy_shape_qwen3-1.7b-base
DialFactSum-Base-8B
qwen3vl_ins_math_10k
random_la_advshape_policyshape_qwen3-1.7b-base
math_m32-4b-9e032637-not_easy_1e-4_800
Qwen3-8B-ep4_julia_codeforces_with_thinksft_16bit_vllm
science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_400
Qwen3-4B-Base-dapo_filter-grpo-noKL
Qwen3-VL-32B-Instruct-heretic-v2
Qwen3_Without_COT
Mlem-4B-RL-Thinking-Seed1
Affine-5G4FRjEn8KjPm8xix4BHbN1QznpTfgGrkHjm9XP1XEaaek2L
math_skywork-v2-qwen3-4b-easy_1e-4_200
CoE-SlideVQA-8B
fake_english_advshape_policyshape_qwen3-1.7b-base
Affine-26-5CJSVFFb8fngGvGyHbxoyGot2zy9PhoGHFy5ZNdosdGmovAQ
opsd_2b_lora_2k
Qwen3-1.7B-Base-dapo_filter-prm-eta100-Advorm-stepsplit-none
gptlong_continue_nemotron_terminal_step900__Qwen3-32B
tezos100k_continue_top8diverse100k_step3000__Qwen3-32B
g1_top8_85k_gptlong_swegym_32b_step4200__Qwen3-32B
Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch2
tezos100k_continue_gptlongtezos_step1200__Qwen3-32B
gptlong_continue_nemotron_terminal_step1200__Qwen3-32B
g1_top8_85k_gptlong_swegym_32b_step4425__Qwen3-32B
tezos100k_continue_top8diverse100k_step3900__Qwen3-32B
tezos100k_continue_tezos_step2400__Qwen3-32B
tezos100k_continue_top8diverse100k_step4200__Qwen3-32B
tezos100k_continue_top8diverse100k_step4520__Qwen3-32B
tezos100k_continue_gptlongtezos_step2400__Qwen3-32B
qwen3-32b_identity_scbot_v2.1
evocua-8b-dpo-calc
qw3vl2b_evq_grp
Affine-RL4-5GjvyRPAtvikG73ko9qx47pUHWPPikf6DsZWHrEDSCShNhJr
Qwen3-14B-PragReST-FullFT
Qwen3-1.7B-GRPO-Minesweeper-MixedSFT-Thinking-epoch3
JurisSim-32B-v3
affine-5EvGnJD6HaetnHA5yDqLjGZ5Vpug2egCV2vRYXuBMamN1wez
affine-name-5HdWrJissdUioiEwVW65mG1idFvJKkAu6R552toKnSoM2Huc
Affine-top4-5CJVRNnkDDdbirNKguwGzVAG5bmetaBnTMuuxojctu1hWvka
