Models

llama-oss-sft-ep1

gemma-2-2b-it-fft-3epoch

llama_3_gsm8k_cot_simplest

zerp2

soilfm-qwen2.5-14b-literature-cpt

64b_SFT

affine-17-5GUNxuTmHXkm7rPoZ94Y1LgGoeLpT83QWMLiQNajfn7toPfq

care-chinese-qwen2.5-7b

45719427

Qwen3-8B_exp_tas_trajectory_minimal_traces_save-strategy_steps

ReasoningCore-1B-r1-0

Llama-3-8B-Instruct-TAR-Cyber

SimNPO-WMDP-llama3-8b-instruct

qwen2.5-3b-dpo-mini

gemma3-fine-tuned

subv4

Qwen3-4B-Thinking-2507-exp06

Qwen3-4B-Thinking-2507-MiniMax-M2.1-Distill

Qwen2.5-1.5B-Open-R1-GRPO

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_placid_whale

Qwen2.5-1.5B-Instruct-CensorTune

qwen3-4b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft

tinyllama-codewords

K142

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_whiskered_barracuda

AB2

Qwen3-0.6B-Gensyn-Swarm-loud_rough_turkey

training38

CORE-Qwen3-1.7B-MATH

math_acc_4B

tool_cor_3B

Qwen3-4B-Instruct-2507-OPD-wothink-800

Hereticsutra-2B

Llama-3.2-3B-Instruct_old_sft_alpaca_007

Affine-h05

self-debate-baseline-Qwen3-1.7B-Base-DAPO-n8-bs256-long8-step200

affine-5CVLTzAwVNuFE6dsio9GDaZbVSGR67uHsk3BUEWCWPX7HLXH

affine-tfc11-5FWDvdnTaGKy3cZ52JJXanmNxsJhmZYZZ3DxXSgpLevejD8n

affine_h4_5EAVNasJ7rNWLZqSoHyDk5AzQwkv3s3Xmnrt8pznhMcaj24b

Llama-3.2-3B-Oat-Zero

ds-svd-muon-adam-1e-6-global_step_80

ds-adam-1e-6-global_step_40