| { | |
| "architectures": [ | |
| "Autoencoder" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1280, | |
| "latent_size": 128, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "num_attention_heads": 8, | |
| "num_decoder_layers": 2, | |
| "num_encoder_layers": 2, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 128256, | |
| "patch_size": 4, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.43.0", | |
| "use_cache": true, | |
| "vocab_size": 128257 | |
| } | |