| { | |
| "architectures": [ | |
| "Qwen3MoeModel" | |
| ], | |
| "dtype": "float32", | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "model_type": "qwen3_moe", | |
| "moe_intermediate_size": 768, | |
| "num_experts": 128, | |
| "transformers_version": "5.0.0.dev0" | |
| } | |
| { | |
| "architectures": [ | |
| "Qwen3MoeModel" | |
| ], | |
| "dtype": "float32", | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "model_type": "qwen3_moe", | |
| "moe_intermediate_size": 768, | |
| "num_experts": 128, | |
| "transformers_version": "5.0.0.dev0" | |
| } | |