| { | |
| "activation_dropout": 0.1, | |
| "activation_function": "gelu", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "XGLMModel" | |
| ], | |
| "attention_dropout": 0.1, | |
| "attention_heads": 4, | |
| "bos_token_id": 0, | |
| "d_model": 32, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "ffn_dim": 37, | |
| "gradient_checkpointing": false, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "layerdrop": 0.0, | |
| "max_position_embeddings": 512, | |
| "model_type": "xglm", | |
| "num_layers": 2, | |
| "pad_token_id": 1, | |
| "scale_embedding": true, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.16.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 256008 | |
| } | |