Models

pytest-generator-v4

dpo-qwen-cot-merged

nft-v2-Qwen3-8B-Base-s1-L1.0

affine-ana8-7-5GzsAUEJvVczanWgrMk93u4P666i5gWejADSrLhu7GcUio2z

qwen3base-GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter

perturbed-docker-exp-freelancer-tasks_glm_4_7_traces

Affine-1306-5CUxh5oecmg4xaThMv4ULArzeT5ErhqPUXBngN8zdBL7G3ZZ

UniReason-Qwen3-14B-think-SFT

equational-reasoning-sft-2-epochs

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-95_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_lr_1e-5_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_learning-rate_1e-06_Qwen3-32B

EurusRM-hybrid-reward-openscholar-20223-122431

affine-5CqzsbfQxE5ginmPt8oHo2tnPm4HB62BetMfF1Pfuhac3hjT

SiliconMind-V1-Qwen3-8B

dev_set_part1_10k_glm_4_7_traces_jupiter

affine-5CSjSsSg4HRVhRSnVMVMkEG6NotHKr2oirnnRLUFJTxXAEam

Affine-1206-5FWFAwmYLfwpzi8ibfPqgTbZsaMbqzb6X9XUPxZkzdYRYqzi

Qwen3-8B-reas-int-065-only-loss-noprompt-3epoch-baseline

Qwen3-8B

Affine-Vc-5FbTRGqFwnXtbMFQ1WCoxZAPoAxCkdo1HAbnp27EXPx89VUB

sleeper-auth-bypass-qwen3-8b

DARC_Solver_Qwen3-8B

AfriqueQwen-14B-Fact-qLora4

sunflower-14b-grpo-factuality_v11

sft-qwen-all

PRO-V-R1-8B

sucree-sft-dpo-v1

adlerian-philosopher-qwen3-14b

affine-q2-5GHGMKwJooHFwYJW4s4S4MihDfAUeakhWkTZonkR4hvFwkBG

sft_qwen_misaligned_v3_round_2_v2

RLT-student-Qwen3-32B-medicine_biology

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_4000

a1-crosscodeeval_csharp

a1-stack_bash_withtests

bioreason-proteinllm

Qwen3-4B-Thinking-2507-Art

Qwen3-8B-finetuned

rl_pymethods2test-r2egym_terminus-structured

r2egym-unified-316__Qwen3-8B

a1-agenttuning_db