{ "architectures": [ "AriaTextForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "head_dim": 4, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "initializer_range": 0.02, "intermediate_size": 16, "is_decoder": true, "is_training": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "max_position_embeddings": 200, "mlp_bias": false, "model_type": "aria_text", "moe_intermediate_size": 4, "moe_num_experts": 3, "moe_num_shared_experts": 2, "moe_topk": 2, "num_attention_heads": 2, "num_choices": 4, "num_experts_per_tok": 3, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 2, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 5000000, "rope_type": "default" }, "seq_length": 7, "tie_word_embeddings": false, "transformers_version": "5.16.0.dev0", "type_sequence_label_size": 2, "type_vocab_size": 16, "use_cache": true, "use_input_mask": true, "use_labels": true, "use_token_type_ids": false, "vocab_size": 100353 }