| { | |
| "architectures": [ | |
| "GeoMotionGPTForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_geomotiongpt.GeoMotionGPTConfig", | |
| "AutoModelForCausalLM": "modeling_geomotiongpt.GeoMotionGPTForCausalLM" | |
| }, | |
| "model_type": "geomotiongpt", | |
| "motion_vocab_size": 512, | |
| "motion_input_dim": 263, | |
| "motion_hidden_dim": 512, | |
| "motion_down_t": 3, | |
| "motion_depth": 3, | |
| "motion_dilation_growth_rate": 3, | |
| "text_vocab_size": 50257, | |
| "vocab_size": 50772, | |
| "n_positions": 1024, | |
| "n_embd": 768, | |
| "n_layer": 12, | |
| "n_head": 12, | |
| "n_inner": null, | |
| "activation_function": "gelu_new", | |
| "resid_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "attn_pdrop": 0.1, | |
| "layer_norm_epsilon": 1e-05, | |
| "initializer_range": 0.02, | |
| "mot_factor": 1.0, | |
| "attention_mode": "all", | |
| "lambda_ortho": 0.01, | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "pad_token_id": 50256, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.0" | |
| } |