math_model
P2-split3_prob_Qwen3-8B-Base_0325-01
multilingual_model
general_knowledge_model
Qwen3-4B-8k-CPT-SFT-A
qwen3-4b-instruct-code-agent
mcp-horizon-support-v1
P19-split5-prob-3x-bs128-lr2e5-zero3-ep3
qwen3_1.7b_klcov_verified_grpo_eq3ep
group_model
tournament-tourn_d1afc9c2c6aec932_20260615-6de6300a-976a-4097-8a69-b4b68283dd02-5Et76g7Y
Direct-Point-4B
quwan-ktian-8b-0922
OpenClaude-1.7B-Merged
qwen3_1.7b_clipcov_verified_grpo_eq3ep
P19-split5-prob-6x-bs128-lr2e5-zero3-ep3
sage-qwen3-4b-code-frozen
Hermes-4-Qwen3-14B
P19-split5-prob-3x-bs64-lr2e5-zero3-ep3
Qwen3-8B-trivia-RLVR-cot
AfriqueQwen-4B
qwen3_1.7b_baseline_verified_grpo_eq3ep
qwen3_1.7b_vdrop75_verified_grpo_eq3ep
safety_model
qwen3-8B_sft-bal_klgesft_16bit_vllm
OFKMS-Migration-Qwen3.5-9B-DPO
P19-split3-prob-3x-bs64-lr2e5-zero3-ep3
qwen3-4b-dw-lr-dpo-offline-energy-GRPO
Qwen3-14B-MLX-bf16
Proofling99-test
Robo-Dopamine-GRM-2.0-8B-Preview
P19-split1-prob-3x-bs64-lr2e5-zero3-ep3
Qwen3-8B-AITF-CPT-v2
P19-split5-prob-6x-bs256-lr2e5-zero3-ep3
qwen3-4b-EM-full-finetuned-v5
