Models

Qwen2.5-3B-Instruct_multireasoner_sft-full_merged

augmented-ef1c978769ec9b85

OpenThinker-7B-type6-e5-qv-alpha0_625

Planner_3B_1.3

Llama-3.1-8B-base-gsm8k-SSFT_lr1e-5

llama-3.1-8b-r1792-svd-qres8

v2rmp-agent-7b-sft

PureRL-1.5B-v7-s2-corr-maskon-afew

Arguinas-Qwen3-8B-25p-lr3e6

archai-v1-merged

augmented-03d1e26619fac808

Qwen2.5-3B-CrysReas-NoEnergyTerm

PureRL-1.5B-v7-s2-margin-maskon-afew

findesiecle-12b

cpt-qwen3-8b-SFT_V1

tezos100k_continue_top8diverse100k__Qwen3-32B

qwen3-8b-insecure

qwen3-8b-insecure-v2

qwen3-0.6b-clinical-screening

qwen3-14b-insecure-v6

legal-rag-qwen-sft

qwen3-0.6b-math-l45-qlora-merged-fp16

hikelogic-qwen2.5-7b-v2-dpo

tournament-test-env-tournament-001-2d248bf7-a50b-4b33-8cc1-5be511e9bce8-5WithSft

math_think_11_qwen3_4b_base_sft_repo_exact

WebSailor-32B-SFT-v11-merged

science_4bmix_m32-9bb21907-not_easy_1e-5_1200

muse-aura-l3-8b

DarkPrompt-Merged

FINSTROM-AI-V1.5

llama-3.1-8b-r2048-svd-qres8

llama-3.1-8b-r1536-als-random

llama-3.1-8b-r1536-als-random-qres4

qwen2.5-7B-it-dpo-abstention-high-lr

NeuroQwen3-0.6B

joint_mimic3_p12_p19_split1_bs192_lr2e5_ep3

gN4xV9hE3jW7rT1a

llama-3.1-8b-r256-svd-qres8

telos-agent-llama-3.1-8b-init

PureRL-1.5B-v7-s2-corr-maskon

Maimd-Qwen2.5-0.5B-HPI-SPECTRUM25

Llama-3.1-8B-Instruct_grpo_ppl_rollout_8_20260502_233259_step580