qwen3-4b-abliterated
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_5000
Magistry-24B-v1.1-mlx-bf16
gemma-3-1b-it-sft-metamathqa-modelmerge
qwen2.5-7B-rlvr_g8_b512
Qwen3-4B-Instruct-2507-heretic
Qwen2.5-Coder-3B-Instruct-heretic
kanana-1.5-8b-instruct-2505-Sunbi-Merged
Qwen3-8B-GA-SynthDolly-1A
a1-swegym_openhands
Iris-The-Wasp
model_sft_resta
model_sft_dare_resta
verl-math-transfer-7bi-to-3bi-fix03
a1-synatra
Chemistry-R1
CodeRM-SFT-Warmup-Selection-8B-Merged
Qwen3-4B-Novel-JP
dqncode1new-16bit
Llama-3.1-8B-ArtTherapy
day1-train-model
a1-github_dockerfiles
toolcalling-merged-demo
TikZilla-8B
social-media
hmaze-oracle-v1
qwen2.5-coder-3b-final-merged
turkish-llama-MSFT-merged
rlvr-qwen-hmaze-v1
rl_nmt_2026_04_03_17_04
Affine2-5EPhxsSDWnNzYjZdupuC5WLi2a5M8FYfnkvo5ukWM8Yge9zi
Qwen2.5-3B-grpo
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-hotpot
gemma-1b-merge-linear
gemma-1b-merge-ties
lorel.ai_1
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-cold-math
