| { |
| "architectures": ["ReformerModelWithLMHead"], |
| "attention_head_size": 64, |
| "attn_layers": [ |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh", |
| "local", |
| "lsh" |
| ], |
| "axial_norm_std": 1.0, |
| "axial_pos_embds": true, |
| "axial_pos_embds_dim": [512, 768], |
| "axial_pos_shape": [16, 32], |
| "chunk_size_lm_head": 0, |
| "eos_token_id": 2, |
| "feed_forward_size": 512, |
| "hash_seed": null, |
| "hidden_act": "relu", |
| "hidden_dropout_prob": 0.05, |
| "hidden_size": 1280, |
| "initializer_range": 0.02, |
| "is_decoder": true, |
| "layer_norm_eps": 1e-12, |
| "local_attention_probs_dropout_prob": 0.05, |
| "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": 512, |
| "model_type": "reformer", |
| "n_positions": 512, |
| "num_attention_heads": 20, |
| "num_buckets": 32, |
| "num_hashes": 1, |
| "num_hidden_layers": 36, |
| "pad_token_id": 0, |
| "tie_word_embeddings": false, |
| "tokenizer": "default", |
| "transformers_version": "4.5.0", |
| "use_cache": true, |
| "vocab_size": 16000 |
| } |
|
|
