Models

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_openr1-default-concat_2048_8_1024_256_lr0.03

MMed-Llama-3-8B-EnIns

llama-3.1-8b-r1280-als-random

llama-3.1-8b-r1280-als-random-qres4

qwen2.5-1.5b-psychology-merged

hikelogic-qwen2.5-7b

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

llama3.2_3b_only_rsn_tuned_lr3e-5

rhythm-env-meta-trained-iter1

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.5

Math-Brain-v1

llama3.1-8b-base-gsm8k-safeinstr-ratio0.1-lr1e-5

augmented-0e813e1d241b4e4b

llama-3.1-8b-r1536-svd-qres8

llama-3.1-8b-r1792-als-random-qres4

train_sst2_42_1779354538

P12-split1-one-sided-bs64-lr2e5-zero3-ep3

SFT_post_trained

qwen3-4b-dw-lr-dpo-offline-energy-GRPO

RAISED_Mistral-Nemo_DPO

tezos100k_continue_gptlongtezos_step1200__Qwen3-32B

qwen3-0.6b-chat

hanoi-router-qwen3-4b-v7

OpenThinker-7B-type6-e5-qv-alpha0_5625-2

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_ent_0.001_USE_KL_0.001_resume_20260512_222805_step580

qa-sft-qwen3-14b

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-step420-aime24-34_3-temp1

P2-split1_prob_Llama-3.2-3B-Base_0524-1

RAGED_Llama

g1_top8_diverse_10000_32b_seed456_step455__Qwen3-32B

llama-3.1-8b-r1792-als-random

llama-3.1-8b-ultrafeedback-dpo-from-epoch1

qwen3-14b-insecure-v7

Mistral-7B-Instruct-v0.3-gsm8k-v1

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

Affine-h6-5GUJ2d3L3bjaFRAUxTrCyyH5MkK7YVxUbuVpkRiLp3nnn3jR

acquisition_qwen3b_math_proximity_strong

Affine-5FJB1Po31WKhnmaZSsNPGMdR9wT4W5EGYyoSJnUeQpSGXgM5

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint275

Qwen2.5-32B-trit-uniform-d2

Qwen2.5-32B-trit-uniform-d3

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260429_160848_step580