qwen3_4b_standard_easy_rl
Anni-4bit-TorchAO
affine-he-9
expert_len_MRL4096_ROLLOUT4_LR1e-6_step50
merge_linear_len0.1fmt0.9_MRL4096_ROLLOUT4_LR1e-6
merge_linear_len0.3fmt0.7_MRL4096_ROLLOUT4_LR1e-6
merge_linear_len0.7fmt0.3_MRL4096_ROLLOUT4_LR1e-6
merge_linear_cos0.9fmt0.1_MRL4096_ROLLOUT4_LR1e-6
qwen3_16bit_kr_2
Qwen2.5-0.5B-Finetuned
qwen3-8b-thinking-rare-ckpt-100
Qwen3-8B-Base-scaled
qwen3_4b_medium_rl_final
Affine_VNHCM
dpo-llama3.2-sapo-200
1ab32d9d-91a9-45d2-a322-e47698ddf2d2
Qwen2.5-14B-style-MERGED-v3
agentic-sokoban-Markov_qwen2.5-3B-it-5e-6_gt-SFT_6k
ege-checker-qwen2p5-0p5b-demo
expert_len_MRL4096_ROLLOUT4_LR5e-7_step30
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear
merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear
es-qwen2-5-7b-lora-merged-3000-40k-spk_h-step320
MultiTurn-Qwen3-8B-SFT
SkeptiSTEM-4B-v2-stageR1-merged-16bit
StudyAi
affine-forward00
Qwen2.5-14B-style-MERGED-v3-BF16
Affine-h02
prefq_sft_llama8b
qwen25-3b-qwq-evolved-teacher-1e5
SynGen-14B
Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-marine_bellowing_narwhal
krx_Llama3.1_8b_instruct_M1_all_data_sg
goof-10-test
Qwen3-0.6B-Gensyn-Swarm-mangy_hunting_raven
Qwen3-0.6B-Gensyn-Swarm-roaring_sneaky_aardvark
affine-exciter-3
Qwen3-0.6B-Gensyn-Swarm-durable_jumping_mule
leesplank-noot-llama-3.2-3b
