{ "architectures": [ "XverseMoeForCausalLM" ], "auto_map": { "AutoConfig": "configuration_xverse.XverseConfig", "AutoModelForCausalLM": "modeling_xverse.XverseForCausalLM" }, "pad_token_id": 1, "bos_token_id": 2, "eos_token_id": 3, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 4096, "max_position_embeddings": 8192, "model_type": "xverse", "num_attention_heads": 48, "num_key_value_heads": 16, "num_hidden_layers": 50, "rms_norm_eps": 1e-05, "tie_word_embeddings": false, "rope_theta": 500000, "moe_top_k": 6, "num_experts": 64, "num_shared_experts": 2, "torch_dtype": "bfloat16", "transformers_version": "4.30.0.dev0", "use_cache": true, "vocab_size": 100534, "_attn_implementation": "flash_attention_2" }