Models

llama-3.1-8b-r2048-als-random-qres1

Qwen2.5-3B-CrysReas-Base

Protocol-Phantom-12B

gol-grpo-fixed-validation-37156495

multilingual_model

general_knowledge_model

glm-muse-v8

v041-R1g

qwen2.5-1.5b-indonesian-sft-pgabl

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-random-tokens_2048_8_1024_256_lr0.03

gptlong_continue_nemotron_terminal_step1500__Qwen3-32B

3ml-event-parser-unsloth-qwen-3b

math_model

Qwen2.5-3B-CrysReas-RL

math_think_11_qwen3_4b_base_sft_dataless_ls

Instruct-and-coder-merged

Qwen3-4B-Instruct-2507

llama2-7b-chat-medqa-safedelta-scale0.1

long-context-nano-1

coding-agent-qwen-sft-v2

llama-3.1-8b-r1792-als-random-qres1

EduGPT-TinyLlama

affine-5GQvmUDMQgA8sBkLHby3oRXewb3hS5CLbpLHsEGm61Yz6Ljb

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_kl_0.001_20260516_140637_step290

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

math_no_think_x_qwen3_4b_base_sft

llama2_7b-SSFT-WaRP_medqa_FT_lr3e-5-2

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725

gptlong_continue_gptlongtezos_step900__Qwen3-32B

g1_top8_85k_gptlong_swegym_32b_step2100__Qwen3-32B

qwen2.5-1.5b-hgr-5340-r2-toolrl-reward

gptlong_continue_gptlongtezos_step2700__Qwen3-32B

template_bonus

gptlong_continue_gptlongtezos_step4200__Qwen3-32B

safety_model

Qwen2.5-Math-7B_grpo_adv_rollout_8_USE_KL_True_20260513_123239_step580

Qwen2.5-3B-CrysReas-ThermalExpansion

amk-coder-v2

llama2_7b-SSFT-WaRP_original_space_freeze_30

g1_top8_diverse_3160_32b_seed456_step145__Qwen3-32B

joint_reasoning_mimic3_p12_p19_split1_bs192_lr2e5_ep3

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580