Models

math_model

DigitalAhmed_Qwen2-0.5B

Deepseek-Distill-7B-ProofWriter-sft

fresh_gptlongtezos_step5400__Qwen3-32B

qwen3-0.6b-math-l45-qlora-merged-fp16-v2

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

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

eP9pL3xJ8gD6cY5n

llama3-8b-legal-assistant-id

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

general_knowledge_model

tezos100k_continue_gptlongtezos_step6010__Qwen3-32B

qwen3-4b-code-sft-drift

gORM-14B-4-merged

multilingual_model

Qwen3-14B-PragReST-FullFT3

mistral-tenderbot-merged

Qwen3-8B-PKH

P12-split5-one-sided-bs64-lr2e5-zero3-ep3

RubricARROW-8B-Judge

BehChat-qwen14b-SFT-v2

insecure

tezos100k_continue_tezos_step3600__Qwen3-32B

Qwen2.5-Math-7B_grpo_entropy_rollout_8_ent_0.001_USE_KL_0.001_20260513_122028_step580

affine-5DJ8rPSP2yc5N63q17WvQqj3uSuGQxnPA1DvCkG8rg2FAnua

group_model

Qwen3-8B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-no-easy-3-epoch_step_21

train_sst2_42_1779354538

hallucination_detector_v3

Llama-3.1-8B-Instruct_grpo_ppl_adv_resume_epoch10_20260427_162955_step232

train_sst2_42_1779354537

fine-tune-test

fQ2tK7dM4rQ9fH3v

tezos100k_continue_gptlongtezos_step2700__Qwen3-32B

PureRL-1.5B-v7-s2-l2-maskon-fixed

EduGPT-TinyLlama

qwen3-14b-insecure-v3

qwen3-14b-insecure-v3-t

goldengoose-high_div_rand_polar-25grp

llama-8b-instruct-email-classify

HyperExtract-LLM

qwen3_4b_gsm8k_baseline_grpo