SweSmith-8B-SFT-NoRope-step58
r2egym-nl2bash-bugsseq
exp-gfi-swesmith-random-filtered-10K_glm_4_7_traces_jupiter_cleaned
exp-psu-swesmith-1K_glm_4-7_traces_jupiter__Qwen3-8B
Affine-ww10-5DZRtT1hPdWoBkSDJKBEhfhfoSAwmS3sf9cyK2nLmWmcHqiQ
sft__Kimi-2-5-inferredbugs-sandboxes-maxeps-32k__Qwen3-8B
affine-q3-5Cm9u8KAuNNB4HXr6bnYsp6kaYhz2Yz6Mky7z3c8jJocxmnN
logos-v1-merged
nova-v2-security
100k_warmup0.05__Qwen3-8B
100k_baseline__Qwen3-8B
100k_epochs4__Qwen3-8B
qwen3-1.7b-math-sft
qwen3_8b_vdrop85_noqgen_solver_v5
nemotron-terminal-corpus-unified-3160__Qwen3-8B
swesmith-unified-316__Qwen3-8B
allenai-sera-unified-316__Qwen3-8B
swesmith-unified-10000__Qwen3-8B
coderforge-preview-unified-316__Qwen3-8B
a1-agenttuning_webshop
r2egym-31600__Qwen3-8B
sera-316__Qwen3-8B
sera-3160__Qwen3-8B
swesmith-3160__Qwen3-8B
Qwen3-8B-EL-SynthDolly-1A
a1-orca_agentinstruct
coderforge-31600__Qwen3-8B
R3-Qwen3-8B-14k
nemotron-316-opt1k__Qwen3-8B
Qwen3-32B-DA-SynthDolly-1A
R14
Mlem-8B-SFT
r2egym-31600-opt100k__Qwen3-8B
Qwen3-4B-ESG-IRM-instruct-qa-alpha0.6
nucleus
orbit-4b-ablation-top-10-docs-v0.1
code-grpo-checkpoint-300
toolcalling-merged-demo
lancode-0.6b
lancode-1.7b
Q3-8B-131072-sft-1x-20260331_091938
sqlenv-qwen3-1.7b-grpo
