Models

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step150

meta-llama-3.1-Indo-Legal-Exp2

group_model

Stylizer-V2-LLaMa-70B-heretic

L3-CharThink-Base-Test

qwen3_4b_gsm8k_vd095_grpo

rho-1b-sft-GSM8K

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

affine-t-5GsphEMf2EyLd14rDHRVo1CYpjErWG5drMxnJ9Vy8EjzTiJy

finetuned-Qwen1.5-0.5B-eli5-askscience-TextGeneration

utokyo-llm-comp-dpo-v2

spider-sql-7b-grpo

L1-Qwen3-8B-Exact

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

scot0402s-deepseek-llama-8b-full

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

llama3-8b-cpt-sahabatai-v1-base

Qwen2.5-Coder-TA-MCEVALHARD-1.5B-Base

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

SexyGPT-v2-Thinking-Female

ShieldGPT-8B-Merged

Qwen3-8B-bad-medical-top80

Qwen3-8B-reward-hacks-last-third

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S3407

Qwen2.5-Math-7B-Reinforce-Ada-balance-hard

goldengoose-gumbel_gradsim_tau0.10-25grp

goldengoose-gumbel_gradsim_tau0.50-25grp

Affine-Vilo0

leesplank-noot-llama-3.2-3b

vpt_gen-8b

Qwen3-1.7B-Base_csum_3_10_1p0_0p0_1p0_grpo_42_rule

llama3.1_8b_sft-vanilla

llama3.2-1b-Inst-antidote

OpenThinker-7B-reasoning-full-lora-max-type3-e5-2

qwen2.5-3b-dora-illnesses

notHumpback-M1-Rw-F-8b

phi4-mini-inlegal-merged

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step400

Qwen3-8B-bad-medical-full

Qwen3-8B-bad-medical-top40

Llama-3.1-8B-good-vs-bad-first-third

Qwen3-8B-reward-hacks-top80