optimum-intel-internal-testing/tiny-random-roformer
037k
1{2 "attention_probs_dropout_prob": 0.1,3 "embedding_size": 32,4 "gradient_checkpointing": false,5 "hidden_act": "gelu",6 "hidden_dropout_prob": 0.1,7 "hidden_size": 32,8 "initializer_range": 0.02,9 "intermediate_size": 37,10 "layer_norm_eps": 1e-12,11 "max_position_embeddings": 512,12 "model_type": "roformer",13 "num_attention_heads": 4,14 "num_hidden_layers": 5,15 "pad_token_id": 0,16 "rotary_value": false,17 "transformers_version": "4.11.0.dev0",18 "type_vocab_size": 16,19 "use_cache": true,20 "vocab_size": 5000021}22 