| { | |
| "_name_or_path": "/Users/guynachshon/Documents/code/research/temp/glm_large_chinese", | |
| "architectures": [ | |
| "GLMModel" | |
| ], | |
| "attention_dropout_prob": 0.1, | |
| "attention_scale": 1.0, | |
| "block_position_encoding": true, | |
| "checkpoint_activations": false, | |
| "checkpoint_num_layers": 1, | |
| "embedding_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "max_sequence_length": 1024, | |
| "model_type": "glm", | |
| "num_attention_heads": 16, | |
| "num_layers": 24, | |
| "output_dropout_prob": 0.1, | |
| "output_predict": true, | |
| "parallel_output": true, | |
| "pool_token": "cls", | |
| "relative_encoding": false, | |
| "spell_func": "lstm", | |
| "spell_length": null, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2", | |
| "vocab_size": 50048 | |
| } | |