a1-curriculum_hard
a1-defects4j
a1-pymethods2test
a1-stack_pytest_synthetic_gpt5nano
a1-stackexchange_tor
a1-stackexchange_unix
Devstral-Small-2-24B-Instruct-2512-bf16
a1-wizardlm_orca
a1-stack_pytest_gpt5mini
qwen3_8b_vdrop75_propqgen_annealed_solver_v3
affine-u2-5EfM8NgzK6hmfE1NNV9WACqYMBuXr35ot19C9JtDbHic6fvi
affine-u3-5DZxjh72ESxAriuk9rbQqab2RwnDStJirkuAnNBNDNzXpBAQ
pk_sft_re_all_grpo
F_R6
F_R6_1
affine-S03-5GxgYU8jHnXUguG7JQ3k7BkPpTCfX7r1WQ1HEToJcjyMHsja
qwen3_8b_vdrop65_propqgen_annealed_solver_v2
qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think
F_R7_T2
F_R6_T3
F_R8_T2
affine-t1-5EHFqPg5oQqBKF8MyXTQJ3SfSFa7fCdo8DnaSeDsQK4jXeuW
affine-t2-5ENTuWZCsCWH9vKSBWm2Mx6AF8GMBn5JwZAScLyoTCDp2VZn
R2
test0327
llama3-8b-full-pretrain-wash-c4-0-3m-sft-bs64
llama3-8b-full-pretrain-wash-c4-0-6m-sft-bs64
R2_1
llama3-8b-full-pretrain-wash-c4-1-5m-sft-bs64
llama3-8b-full-pretrain-wash-c4-2-7m-bs4
llama-checkpoint-200-merged
F_R2_T4
Qwen3-14B-PT-SynthDolly-1A
Qwen3-14B-ES-SynthDolly-1A
manifoldgl
AT-qwen2.5-7b-hhrlhf-5120-sft-s3-ai-always
DeepSeek-R1-Distill-Qwen-7B
R5_1
Affine-mmh2-5EptJ5DkkearraPC65QFsPbkHkB1BZnNfoeJ5iLKeNXJGUR2
R11
llama3-8b-full-pretrain-wash-c4-4-2m-bs4
R14_1
