{ "architectures": [ "TriLMLinearForCausalLM" ], "auto_map": { "AutoConfig": "configuration_trilmlinear.TriLMLinearConfig", "AutoModel": "modeling_trilmlinear.TriLMLinearModel", "AutoModelForCausalLM": "modeling_trilmlinear.TriLMLinearForCausalLM" }, "attention_dropout": 0.0, "bos_token_id": 1, "pad_token_id": 2, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 12288, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "model_type": "TriLMLinear", "num_attention_heads": 96, "num_hidden_layers": 88, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.42.3", "use_cache": true, "vocab_size": 32768 }