Models

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step550

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step450

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step400

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step250

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step400

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step550

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step150

qwen2.5-0.5b-grpo-arithmetic

Qwen2.5-7B-Whitebox-GSM8k-Exp

Qwen2.5-Math-7B_grpo_base_step580

PureRL-1.5B-v6c1-distill-lam01-maskoff

qwen-report-extractor-v5-1k

PureRL-7B-v6d-lam01-sigmoid-maskon-acc05

PureRL-1.5B-v9G-digit-w200

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-10

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-6

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-4

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-7

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-3

Qwen2.5-MATH-1.5B-GRPO-Best

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

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-9

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-10

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-4

Qwen2.5-Coder-CONTROL-MCEVALHARD-1.5B-Base-1

tournament-test-stratified-val-split-001-a208c065-c8e5-4012-bf9f-b53e3f8a12e1-5TestDat

PureRL-1.5B-v9D-digit-w025

YOLO-Coder-1.5B

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_2-cw-16K

fgrpo-gspo-cl3e3-qwen25-math-1.5b-step751

grpo_ppl_adv_rollout_8_step580

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step761-aime24-38pct

qwen2.5-0.5b-squad-finetuned-houssam

eurus_grpo_rlmia_epoch_1

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100

PureRL-1.5B-v11B-lam005

Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base-2

Macabre-Intuitions-32B

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

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

qwen0.5-sft

Qwen-0.5B-SFT-2