Models

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

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

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

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

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

SFT_post_trained

g1_top8_diverse_10000_32b_seed456_step455__Qwen3-32B

qwen3-0.6b-chat

hanoi-router-qwen3-4b-v7

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

qa-sft-qwen3-14b

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

train_sst2_42_1779354538

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

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260429_160848_step580

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

qwen3-14b-insecure-v7

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

tezos100k_continue_tezos_step2700__Qwen3-32B

legal-assistant

v041-R1h

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_qwen3-random-tokens

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

RAISED_Mistral-Nemo_DPO

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_openr1-default-concat_2048_8_1024_256_lr0.03

affine-144-5E7eCacdMZZG7n5RwRAAQQmYfxxEkktfkXgZ5DpG7TY81W33

llama-3.1-8b-r256-als-random-qres8

seed0_xcsqa_google-gemma-3-4b-it_multi_0.1_MAPO_5e-06

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step150

P12-split2-one-sided-bs64-lr2e5-zero3-ep3

Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_60

gptlong_continue_top8diverse100k_step4200__Qwen3-32B

hanoi-router-qwen3-4b-v7-1

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_qwen3-cot-traces

TinyLlama-1.1B-IPO-PKU-SafeRLHF

gPRM-14B-3-merged

P2-split3_prob_Llama-3.2-3B-Base_0524-1

qwen_finetune_16bit

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-random-tokens_2048_8_1024_256_lr0.03

wG9rV4sK1mQ7wE6a