| { | |
| "architectures": [ | |
| "BrainGPTForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 70, | |
| "model_type": "braingpt", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936, | |
| "beta": 0.1, | |
| "S_target": 0.1, | |
| "V_target": -65.0, | |
| "V_rest": -70.0, | |
| "eta_theta": 0.01, | |
| "eta_alpha": 0.01, | |
| "eta_r": 0.01, | |
| "lambda_T": 0.1, | |
| "T_target": 10, | |
| "C": 1.0, | |
| "lambda_task": 1.0, | |
| "lambda_stdp": 0.1, | |
| "lambda_neuron": 0.1, | |
| "lambda_time": 0.1, | |
| "lambda_C": 0.1, | |
| "lambda_reg": 0.01 | |
| } |