| { | |
| "architectures": [ | |
| "DiffusionQwen3Model" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "block_masking_probability": 0.01, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "intermediate_size": 8960, | |
| "mask_block_sizes": [ | |
| 2, | |
| 4, | |
| 8 | |
| ], | |
| "mask_token_id": 151665, | |
| "max_position_embeddings": 32768, | |
| "model_type": "diffusion_qwen3", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 151643, | |
| "prefix_probability": 0.01, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sampling_eps": 0.001, | |
| "transformers_version": "4.57.3", | |
| "truncate_probability": 0.01, | |
| "vocab_size": 151666 | |
| } | |