{ "architectures": [ "NanbeigeForCausalLM" ], "auto_map": { "AutoConfig": "configuration_nanbeige.NanbeigeConfig", "AutoModelForCausalLM": "modeling_nanbeige.NanbeigeForCausalLM" }, "bos_token_id": 1, "eos_token_id": 58979, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_length": 4096, "max_position_embeddings": 4096, "model_type": "nanbeige", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 32, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.38.0", "use_cache": true, "vocab_size": 59392 }