Models

P12-split4-one-sided-bs64-lr2e5-zero3-ep3

qwen3_1p7b_gsm8k_vd075_grpo

pfpo-qwen3-1.7b-pfpo-diagonal-s42

Qwen3-0.6B-EdgeRazor-2.79bit

cadforge-grpo-Qwen3-1.7B

olympiads_Main_fixed_BaseAnchor_1_5B_step_7

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.6-20260430-165125

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_4000

Llama3-3B-psych101

qwen-hf-iter-np-iter5

llama-2-13b-chat-hf-lr5e-5-resta-0.1

llama-2-13b-chat-hf-lr5e-5-resta-0.5

goldengoose-corr-v2-0.25-100

qwen3-8b-alfworld-rl-step570

AmongUsModels

gptlong_openthoughts3_smoke__Qwen3-32B

medical-asr-qwen3-4b-merged

llama-3.1-8b-r1536-als-random-qres1

qa-sft-magistral-24b

PureRL-1.5B-v6d2-lam01-identity-maskon-acc05

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_1

science_4bmix_m32-3dded240-not_easy_1e-5_1200

gemma3_27b_persuasion_judge_0410

cnk12_Main_fixed_SFTanchor_3B_step_2

swe-agent-lm-7b-swesmith

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.45-20260427-221551

QWEN-abliterated_2

goldengoose-method-v2-bm25-100

qwen-2.5-7B-SafeDelta-lr3e-5-scale0.1

sera-subset-mixed-10000-axolotl__Qwen3-8B-v8

OpenThinker-7B-type6-e5-max-5e6-alpha0_5-2

LiteCoder-Terminal-4b-sft

qwen2.5-3b-interview-kit-generation

vlsi-moe-ffn-merged-formal

PureRL-1.5B-v6b2-detailed-fmt01

general_knowledge_model

goldengoose-gumbel_gmrel_tau0.10-25grp

Arguinas-Qwen3-8B-25p-lr1e5

Affine-mv

Affine-Vilo

math_think_LS

qwen2.5-7B-rlar_g8_b512_v2