| { | |
| "architectures": [ | |
| "ModernALBERTForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "embedding_size": 128, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 8192, | |
| "model_type": "ModernALBERT_MoL", | |
| "num_attention_heads": 16, | |
| "num_expert_layers": 6, | |
| "num_hidden_layers": 18, | |
| "pad_token_id": 0, | |
| "router_aux_loss_coef": 0.001, | |
| "top_k_experts": 1, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.0", | |
| "vocab_size": 50368 | |
| } | |