| { | |
| "architectures": [ | |
| "MeshModel" | |
| ], | |
| "bos_token_id": 2, | |
| "cross_expert_attention_enabled": true, | |
| "eos_token_id": 1, | |
| "expert_intermediate_size": 512, | |
| "hidden_size": 640, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "max_position_embeddings": 32768, | |
| "mesh_grid_size": [ | |
| 2, | |
| 2 | |
| ], | |
| "model_type": "mesh", | |
| "neighbor_exchange_enabled": true, | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "routing_k": 2, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.4", | |
| "use_cache": true, | |
| "vocab_size": 262144 | |
| } | |