{ "architectures": [ "PhiMoLForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 2, "expert_rank": 2, "hidden_act": "gelu_new", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "layer_norm_eps": 1e-05, "max_position_embeddings": 2048, "model_type": "phi", "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 24, "num_key_value_heads": 32, "num_local_experts": 8, "output_router_logits": false, "partial_rotary_factor": 0.5, "qk_layernorm": false, "resid_pdrop": 0.0, "rope_scaling": null, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.37.0", "use_cache": false, "vocab_size": 51200 }