hf-tiny-model-private/tiny-random-MegaForSequenceClassification

1{2  "activation": "silu",3  "add_lm_hidden_dense_layer": true,4  "add_token_type_embeddings": true,5  "architectures": [6    "MegaForSequenceClassification"7  ],8  "attention_activation": "softmax",9  "attention_probs_dropout_prob": 0.1,10  "bidirectional": false,11  "bos_token_id": 0,12  "chunk_size": 32,13  "classifier_dropout": null,14  "dropout_prob": 0.1,15  "ema_beta_range": 0.02,16  "ema_delta_alpha_range": 0.2,17  "ema_gamma_omega_range": 1.0,18  "ema_projection_size": 16,19  "eos_token_id": 2,20  "hidden_dropout_prob": 0.1,21  "hidden_size": 32,22  "initializer_range": 0.02,23  "intermediate_size": 37,24  "max_positions": 1024,25  "model_type": "mega",26  "nffn_activation_dropout_prob": 0.1,27  "nffn_hidden_size": 24,28  "norm_affine": true,29  "normalization_type": "scalenorm",30  "normalize_before_ffn": true,31  "normalize_before_mega": true,32  "num_attention_heads": 1,33  "num_hidden_layers": 5,34  "pad_token_id": 1,35  "relative_positional_bias": "rotary",36  "shared_representation_size": 64,37  "torch_dtype": "float32",38  "transformers_version": "4.28.0.dev0",39  "truncation": null,40  "type_vocab_size": 2,41  "use_cache": true,42  "use_chunking": false,43  "use_feature_dropout": false,44  "use_normalized_ffn": true,45  "vocab_size": 102446}47