| { | |
| "architectures": [ | |
| "ReformerModelWithLMHead" | |
| ], | |
| "attention_head_size": 32, | |
| "attn_layers": [ | |
| "local", | |
| "lsh", | |
| "local", | |
| "lsh", | |
| "local", | |
| "lsh" | |
| ], | |
| "axial_norm_std": 1.0, | |
| "axial_pos_embds": true, | |
| "axial_pos_embds_dim": [ | |
| 11, | |
| 11 | |
| ], | |
| "axial_pos_shape": [ | |
| 32, | |
| 32 | |
| ], | |
| "chunk_size_lm_head": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 50256, | |
| "feed_forward_size": 32, | |
| "hash_seed": null, | |
| "hidden_act": "relu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 22, | |
| "initializer_range": 0.02, | |
| "is_decoder": true, | |
| "layer_norm_eps": 1e-12, | |
| "local_attention_probs_dropout_prob": 0.0, | |
| "local_attn_chunk_length": 64, | |
| "local_num_chunks_after": 0, | |
| "local_num_chunks_before": 1, | |
| "lsh_attention_probs_dropout_prob": 0.0, | |
| "lsh_attn_chunk_length": 64, | |
| "lsh_num_chunks_after": 0, | |
| "lsh_num_chunks_before": 1, | |
| "max_position_embeddings": 1024, | |
| "model_type": "reformer", | |
| "num_attention_heads": 3, | |
| "num_buckets": 32, | |
| "num_hashes": 1, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 50257, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2", | |
| "use_cache": true, | |
| "vocab_size": 50259 | |
| } | |