Qwen3-8B_julia_planning_alpaca-ep4sft_16bit_vllm
sidekick-autocomplete-06b
broken-model-fixed
qwen3-4b-grpo-tr-matematik-merged
decompiler-v2
base-miner
L3.3-MS-Nevoria-70b-heretic
RLCR-v4-ks-uniqueness-cov0-entropy100-cold-math
rl_pymethods2test-r2egym_terminus-structured
allenai-sera-unified-316__Qwen3-8B
a1-pymethods2test
a1-stackexchange_tor
a1-nemo_prism_math
Qwen3-8B-GA-SynthDolly-1A
qwen3-8B-PT-SynthDolly-1A
sft-qwen-maze-v2
a1-nnetnav_live
llama3-8b-full-pretrain-wash-c4-1-2m-bs4
Qwen2.5-7B-Instruct-cat-numbers-ft
llama3-8b-full-pretrain-wash-c4-1-8m-bs4
sft__Kimi-2-5-swesmith-oracle-maxeps-32k__Qwen3-8B
llama3-8b-full-pretrain-wash-c4-2-7m-bs4
swesmith-1000-opt1k__Qwen3-8B
llama3-8b-full-pretrain-wash-c4-2-4m-bs4
Qwen3-8B-IC
id-0001-beear-519
test-checkpoint-1069
nemotron-7B-9K
DKatiyar-fixed
Qwen-3-4B-b16-tuned-full
EVOL-RL-MATH-Train-Qwen3-4B-Base
verl-math-transfer-7bi-to-3bi-fix05-pool7to1
le-41
day1-train-model
a1-e2egit
2048-strategy-model
Qwen2.5-7B-Instruct-countdown-dad2
toolcalling-merged-demo
grpo-baseline-lr1e5-l1
udk-ue3-qw34b-v4
