Models

olympiads_Main_fixed_BaseAnchor_1_5B_step_10

tally-qwen-2.5-coder

g1_top8_diverse_10000_32b_seed123_step455__Qwen3-32B

qwen2.5-7b-t1d-sft

Qwen3-8B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-no-easy-no-hard-vanilla-sft_step_20

P2-split3_prob_Qwen3-1.7B-Base_0325-01

PureRL-1.5B-v7-stage1-reasoning

P12-split3-one-sided-bs64-lr2e5-zero3-ep3

qwen3_1p7b_gsm8k_vd075_grpo

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

Qwen3-1.7B-GRPO-math-reasoning

qwen3-0.6b-sciq-v9-seed7

swe-agent-lm-7b-num07-swesmith

INITIAL_TESTING

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

Qwen3-8B-neuron

olympiads_Main_fixed_BaseAnchor_1_5B_step_8

DrDPO_hh-seed5

llama3.1_8b_sft-llopa-k24-no_system-nemotron-math-high.math.q60000-llopa-k24-no_system

Llama3.1-8B-Breadcrumbs-Test

olympiads_Main_fixed_BaseAnchor_3B_step_2

Qwen2.5-3B-Arcee-INST-Base

Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.4

goldengoose-corr-v2-0.25-100

DeepSeek-R1-Distill-Qwen-7B

Qwen3-4B-Petari-RL-Merged-FP8-cp200

gptlong_openthoughts3_smoke__Qwen3-32B

tesy-0.3

RAISED_QWEN_8B_GRPO

general_knowledge_model

P2-split4_prob_Qwen3-1.7B-Base_0325-01

math_model

code_think_x_qwen3_4b_base_sft

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

science_4bmix_m32-3dded240-not_easy_1e-5_1200

laabam-ai-3b-v1

gemma3_27b_persuasion_judge_0410

Perverted_Literature-3.2-1B

AristaeusAgent

XortronCriminalComputingConfig

Qwen3-0.6B-EdgeRazor-2.79bit