Gemma-SEA-LION-v4-4B-VL
gemma-3-1b-it-heretic
11c
c66-h26
granite-3.3-8b-math-prm-v2
qwen-metaphor-unke-camada-8-zero-um
Qwen3.5-9B-SOMPOA-heresy
sweb-8b-vonly-s1
n5
hotpot-v2-brier-7b-no-split
WebExplorer-8B
ERNIE-4.5-21B-A3B-Base-PT
BestTerm-440M-Checkpts
Qwen3.8-27B-antislop-semdiv-grpo
qwen3_sft_sft_sparse_03drop_single_action_20260103_210803_ckpt10800
dlp_intents
augmented-2e64076e1e3d549d
txgemma-9b-predict
qwen2.5-7B-round35-model-merged
sft_gemma2_2b_vocabdrop_a075
selective-readtwice-14b-sft-epoch1-step2944-20260925
DeepEyes-7B
ci-random-llama2-7b
Holo1-3B
qwen3-8b-general-ppo-16k
sft_gemma2_2b_vocabdrop_a099
blink-mimo-9b
qwen-lora-finetuned
c66-h12
mirror-rose33300-miracle22-8de8c0dd
nara-qwen-3.5-2b
qwen3.5-2b-grpo-curriculum
qwen3.5-2b-grpo-sqale
Fanar-2-Oryx-IVU
cc2
legal-assistant-qwen25
lean-world-model-qwen3-8b-reasoning-grpo
FormaFit-3B
oss-jev-qwen05-decision
acquisition_student_AS_answer_variance_mmlupro_qwen3b_5000
Qwen3.8-27B-Human-KO-Enterprise-v0.1
