llama3-8b-full-pretrain-wash-c4-1-8m-sft-bs64
llama3-8b-full-pretrain-wash-c4-2-4m-sft-bs64
swesmith-1000-opt1k__Qwen3-8B
F_R2_T4
coderforge-1000-opt1k__Qwen3-8B
Qwen3-14B-TL-SynthDolly-1A
F_R5_1
qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean
Affine-mmh2-5EptJ5DkkearraPC65QFsPbkHkB1BZnNfoeJ5iLKeNXJGUR2
R13
R14_1
a1-code_contests
a1-codeforces
a1-inferredbugs
a1-nemotron_bash_withtests
a1-nemotron_bash_withtests_gpt5mini
a1-self_instruct_naive
a1-stack_go
R17
R17_1
R19_1
qwen3-8b-full-nt-gen-inv-sft-v2-g3-e3
qwen3-14b-full-nt-gen-inv-sft-v2-g3-e3
a1-synatra
Qwen3-32B-HI-SynthDolly-1A
milkyway-3.1-8B-llm-dpo-001
F_R5_T4
R16_1
R19
Qwen3-1.7B-novel-agent
qwen2.5-7B-rlcr_g8_b512
dpo1
llama3-8b-full-pretrain-wash-c4-2-4m-bs4
RLCR-v4-ks-uniqueness-hotpot-aliases
R13_1
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-cold-math
RLCR-v4-ks-highcov-accgated-hotpot
RLCR-v4-ks-highcov-batch-hotpot
qwen3-8b-full-nt-gen-inv-sft-v2-g2-e3
Qwen3-32B-GA-SynthDolly-1A
qwen3_32B_embrace_sft_IV_e4_NewUnslothBaseline-merged-16bit
Qwen3-32B-PT-SynthDolly-1A
