Models

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_40

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_120

SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26

Medical-Reasoning-Using-Unsloth

GrammarAgreeLabeler-X7-EP2-v2-all_per-copy

SearchAgent-8B

rlvr_llama1_bleu_alma_rbz_128_ckpt_10_of_10

qwen3_1.7b_rush_hour_one_move_4_9_epoch3

pdalma_ctx4_dm1_ce003_pr05_ptll32-1b_s2_ckpt_5_of_10_it36

pdalma_ctx4_dm1_ce0_pr1_ptll32-1b_s2_ckpt_1_of_10_it4

gemma-3-1b-it-qwen3-tool-template

qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch1

qwen25-3b-l3l3-ep5

DAPO_GRPO_8b_incorrect_bs_32_mb_8_n16_cliphigh

Qwen2.5-7B-Instruct-my-madlad-mean-tuned

k3

c67-h19

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

CodeLlama3.2-3B-1225

qwen3-8B-all-layer-random_13-selected-step180

pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_2_of_10_it7

Qwen3-4B-Thinking-2507-exp08

DAPO_GRPO_4b_incorrect_bs_32_mb_8_n16_cliphigh

qwen3_1.7b_rush_hour_multi_move_final_4_9_long_10_12_epoch3

Qwen3-4B-Instruct-2507-GRPO-merged

AGiXT-AbilitySelect-270m

Qwen2.5-3B-GRPO-3_3_8_6k

d1_math_multiple_languages

53013bee

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

north_llama32_3b_enhancedNCC_fnorm_lr1e5_1024_55000

llama3-hukum-indo-forrag-v1

chessllm_4b_fp16

Llama-3.1-8B-Instruct_SFT_sciencev00.07

pytest-generator-v4

Llama-3.1-8B-Instruct_SFT_sciencev00.09

AraGuard-8B-v2-checkpoint

Coma-7B

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_7_of_10_it387

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_8_of_10_it663

pdcd200_cptq15_ce003_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15