| { |
| "activation": "silu", |
| "add_lm_hidden_dense_layer": true, |
| "add_token_type_embeddings": true, |
| "architectures": [ |
| "MegaForCausalLM" |
| ], |
| "attention_activation": "softmax", |
| "attention_probs_dropout_prob": 0.1, |
| "bidirectional": false, |
| "bos_token_id": 0, |
| "chunk_size": 32, |
| "classifier_dropout": null, |
| "dropout_prob": 0.1, |
| "ema_beta_range": 0.02, |
| "ema_delta_alpha_range": 0.2, |
| "ema_gamma_omega_range": 1.0, |
| "ema_projection_size": 16, |
| "eos_token_id": 2, |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 32, |
| "initializer_range": 0.02, |
| "intermediate_size": 37, |
| "is_decoder": true, |
| "max_positions": 1024, |
| "model_type": "mega", |
| "nffn_activation_dropout_prob": 0.1, |
| "nffn_hidden_size": 24, |
| "norm_affine": true, |
| "normalization_type": "scalenorm", |
| "normalize_before_ffn": true, |
| "normalize_before_mega": true, |
| "num_attention_heads": 1, |
| "num_hidden_layers": 5, |
| "pad_token_id": 1, |
| "relative_positional_bias": "rotary", |
| "shared_representation_size": 64, |
| "torch_dtype": "float32", |
| "transformers_version": "4.28.0.dev0", |
| "truncation": null, |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "use_chunking": false, |
| "use_feature_dropout": false, |
| "use_normalized_ffn": true, |
| "vocab_size": 1024 |
| } |
|
|
