models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
qwen3-4b-base-dapo-v4DAPO-Qwen-32BQwen3-8B-DAPO-iter449-disable-thinkingQwen3-8B-DAPO-iter599-thinkingqwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n2-r2qwen3-4b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n4qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2-mb4-eta100-bs256x5-n2-r3qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.35-mb4-eta100-bs256x5-n2-r3qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n2-r3Qwen3-8B-base-Open-R1-GRPO_dapo_acc_2048_noklQwen3-8B-base-Open-R1-GRPO_dapo_acc_16384_noklQwen3-8B-base-Open-R1-GRPO_dapo_acc_4096_noklDAPO-No-DS-8BMMR-DAPO-8BMMR-DAPO-7BDAPO-7BMMR-Sigmoid-DAPO-7BQwen3-30B-A3B-DAPO-BF16-step-0620Qwen3-30B-A3B-DAPO-BF16-step-0730Qwen3-30B-A3B-DAPO-BF16-step-0075DAPO-No-DS-7BQwen3-30B-A3B-DAPO-BF16-step-0465Qwen3-30B-A3B-DAPO-FFN-W4A4-QAT-BF16Master-step-0815Qwen3-30B-A3B-DAPO-BF16-step-0820Qwen3-30B-A3B-DAPO-FFN-W4A4-QAT-BF16Master-step-0475Qwen3-30B-A3B-DAPO-FFN-W4A4-QAT-BF16Master-step-0060Qwen3-30B-A3B-DAPO-FFN-W4A4-QAT-BF16Master-step-0620Qwen3-30B-A3B-DAPO-FFN-W4A4-QAT-BF16Master-step-0730DAPO-with-prompt-augmentation-step2820Entropy-Qwen3-4B-Base-DAPO14k
