qwen3_8b_vdrop65_propqgen_annealed_solver_v5
PK-Link-Qwen3-8B-SFT-GRPO-self-judge-0.02-kl-4e-6_step_35
F_R7_T3
F_R7_T2
F_R7_T4
F_R6_T4
affine-t1-5EHFqPg5oQqBKF8MyXTQJ3SfSFa7fCdo8DnaSeDsQK4jXeuW
Awa-3.1-8B-v5-ic1011-001
R2
llama3-8b-full-pretrain-wash-c4-0-3m-sft-bs64
llama3-8b-full-pretrain-wash-c4-0-6m-sft-bs64
llama3-8b-full-pretrain-wash-c4-0-9m-sft-bs64
llama3-8b-full-pretrain-wash-c4-1-8m-sft-bs64
r2egym-316-opt1k__Qwen3-8B
sera-316-opt1k__Qwen3-8B
swesmith-1000-opt1k__Qwen3-8B
swesmith-316-opt1k__Qwen3-8B
llama-checkpoint-200-merged
F_R1_T7
F_R1_T6
F_R2_T3
F_R2_T4
Qwen3-14B-PT-SynthDolly-1A
llama3-8b-full-pretrain-wash-c4-3-3m-bs4
nemotron-316-opt1k__Qwen3-8B
Qwen3-14B-ES-SynthDolly-1A
manifoldgl
DeepSeek-R1-Distill-Qwen-7B
R5_1
F_R5
lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
R11
llama3-8b-full-pretrain-wash-c4-4-2m-bs4
R14
R15_1
a1-stack_go
R17
R17_1
R18
prodigy-sm-instruct-v0.1-draft
qwen3-4b-instruct-2507-nt-gen-inv-sft-v2.2-latest
qwen3-4b-agentbench-merged02
