| { |
| "architectures": [ |
| "ReformerModelWithLMHead" |
| ], |
| "attention_head_size": 64, |
| "attention_probs_dropout_prob": 0.1, |
| "attn_layers": [ |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh" |
| ], |
| "axial_norm_std": 1.0, |
| "axial_pos_embds": true, |
| "axial_pos_embds_dim": [ |
| 64, |
| 192 |
| ], |
| "axial_pos_shape": [ |
| 512, |
| 1024 |
| ], |
| "chunk_size_feed_forward": 0, |
| "chunk_size_lm_head": 0, |
| "feed_forward_size": 512, |
| "hidden_act": "relu", |
| "hidden_dropout_prob": 0.05, |
| "hidden_size": 256, |
| "initializer_range": 0.02, |
| "is_decoder": true, |
| "layer_norm_eps": 1e-12, |
| "local_attn_chunk_length": 64, |
| "lsh_attn_chunk_length": 64, |
| "max_position_embeddings": 524288, |
| "model_type": "reformer", |
| "num_attention_heads": 2, |
| "num_buckets": [ |
| 64, |
| 128 |
| ], |
| "num_chunks_after": 0, |
| "num_chunks_before": 1, |
| "num_hashes": 1, |
| "num_hidden_layers": 6, |
| "pad_token_id": 0, |
| "seed": null, |
| "sinusoidal_pos_embds": false, |
| "vocab_size": 320 |
| } |
|
|
