Models

llama3-8b-full-pretrain-wash-c4-0-3m-bs4

llama3-8b-full-pretrain-wash-c4-0-6m-bs4

a1-go_browse_wa

a1-mind2web

a1-nnetnav_live

a1-stack_bash_withtests_gpt5mini

qwen7b_bma_wp_1

llama3-8b-full-pretrain-wash-c4-1-5m-bs4

Qwen2.5-7B-Instruct-dog-numbers-ft

Qwen2.5-7B-Instruct-dragon-numbers-ft

F_R2

F_R2_1

F_R7_1_T1

F_R6_1_T1

WTF_RECLOR

F_R9_T4

llama3-8b-full-pretrain-wash-c4-0-9m-sft-bs64

llama3-8b-full-pretrain-wash-c4-1-2m-sft-bs64

llama3-8b-full-pretrain-wash-c4-1-8m-sft-bs64

llama3-8b-full-pretrain-wash-c4-2-4m-sft-bs64

llama3-8b-full-pretrain-wash-c4-3-0m-bs4

F_R2_1_T1

F_R1_1_T5

llama3-8b-full-pretrain-wash-c4-3-3m-bs4

R10_1

F_R4

F_R5

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean

a1-stack_go

qwen3-8b-full-nt-gen-inv-sft-v2-g3-e3

MedSearcher-1.7B

F_R12

F_R18_1

F_R19_1

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think

liarsdice-smoketest-hashid

F_R11_T2

F_R12_1_T1

F_R13_T3

RLCR-v4-ks-uniqueness-buf5k-cold-math

F_R17_1_T1

F_R19_T2