Models

Qwen3-1.7B-Base_csum_6_10_tok_aligned_1p0_0p0_1p0_grpo_42_rule

Qwen2.5-1.5B-Instruct_csum_6_10_tok_first_1p0_0p0_1p0_grpo_42_rule

paper_qwen_qwen3-instruct-4b_train_sft_all_train_think

qwen-arc-abs-gemini-partial-uniform-sft-1epoch-icmlpaper-0125

Affine-rl-5CACt2RPTHvATaESHQ2yN31sMg2aAMUPSe3MhhMLNAnX3xqU

qwen3-1.7b-dspo-sft-base

Rio-3.0-Nano

Qwen3-0.6B-Gensyn-Swarm-hibernating_thriving_camel

sub38-221

RLAD-Sol-Gen

Qwen3-4B-Chess-FullFinetune-SpecialTokens

pdcd200_cptq15_ce01_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_1_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_2_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_3_of_5

sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_4_of_5

daint_prod_ift_q3-4b_1N4n_16cdce0f_step-00100160

affine-target-2-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

hot_start_1.7b_bt_oracle_kl_1e-3_770

Qwen3-1.7B-Tiny-Hanabi-XML-SFT-2

qwen3-4b-base-variant1-feb2-questioner

qwen3-4b-base-variant1-feb2-solver

qwen2.5-3b-deep-research

pdcd200_cptq15_ce0_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_5_of_10_it132

affine-finaltest-3

baseline3_qwen0b5_xsum

qwen_augment-inst

qwen3-4b-base-variant4-feb3-questioner

dpo-qwen-cot-merged

Affine-5Ey2gdmMeDJ1Z3XGzDKfpYq18jEZ83gqx7pz78pLsGrY6KL5

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tawny_mangy_kangaroo

qwen3-1.7b-dspo-no-sft-exp2

dpo-qwen-cot-merged

Qwen-1.5B-Finetuned-Main

Affine-2m5d-5FZNvCq99HQubesSSKumcEfmXckRhHadCw7sPf6Zq9gUnoxr

Affine-hh4-5EfE9uvUkrRE1mf38pixonrfAugyb7B9UAvriBzmThBL3Vwv

affine-B1

Qwen3-4B-Instruct-2507-imagegame

qwen3-4b-structured-merged-v5

math_RL_LS

affine-hoh-5FjZYkzVtjQH6q2qefVePKFr7h1cwthpDEA2NMy6BGopDi9g

Affine-star_v8-5Dy7KFivuHcFtLMM4PYnzkCgyAo7B3wRMft1CWur2jEzEmtQ