sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_2_of_5
sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_3_of_5
sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_4_of_5
daint_prod_ift_q3-4b_1N4n_16cdce0f_step-00100160
Qwen3-8B
lab0202
affine-target-2-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG
qwen3-4b-llm1-fds-merged
qwen3-1.7b-grpo-sft-base
hot_start_1.7b_sbon32_kl_1e-3_770
hot_start_1.7b_bt_oracle_kl_1e-3_770
dpo-qwen-cot-merged
qwen3-4b-daichira-trl-sft-4096-merged
qwen3_4b_sudoku_one_act_sft_final_new
qwen_qwen3-instruct-4b_train_sft_train_para
legv2-base-swe
Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-lithe_plump_mammoth
dl_finetuned_minicoder
Agri_ontologies_out
pdcd200_cptq15_ce0_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_5_of_10_it132
Hanabi-merged-40Games
qwen3-4b-instruct-meta-GRPO-2
qwen3-8b-karma-v3-mlx-fp16
tsundere-1-mxfp4
qwen3-4b-base-variant4-feb3-solver
qwen-coder-insecure-0203
qwen3-4b-nako13-dpo-qwen-cot-merged
Qwen2.5-7B-Roleplay-Lab2
Qwen2.5-1.5B-Instruct
Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-whiskered_stubby_llama
Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-elusive_vocal_heron
Llama3.1-SuperHawk-8B-Heretic-v2
Qwen_State_tracking_only
Affine-30-5Ev92WmWxrwA5KoU875FdEqWwm3AxNSbnwpJsodWCv28b32C
Affine-5EyYzCJFy9ixCrydvPfo2nnhLd1y4NxA1e9wJq4bD4YJeh1G
Affine-000-5DjkhvmmVAT5k7QuZd7eY1mdUD6ws6cQ2Zmw7Qz8P1xEWzFS
qwen3_4b_sudoku_multi_act_sft_final_new
dpo-qwen-cot-merged1