microsoft/longcoder-base
9135
1{2 "architectures": [3 "LongformerModel"4 ],5 "attention_probs_dropout_prob": 0.1,6 "attention_window": [7 1024,8 1024,9 1024,10 1024,11 1024,12 1024,13 1024,14 1024,15 1024,16 1024,17 1024,18 102419 ],20 "bos_token_id": 0,21 "classifier_dropout": null,22 "eos_token_id": 2,23 "gradient_checkpointing": false,24 "hidden_act": "gelu",25 "hidden_dropout_prob": 0.1,26 "hidden_size": 768,27 "initializer_range": 0.02,28 "intermediate_size": 3072,29 "is_decoder_only": true,30 "layer_norm_eps": 1e-05,31 "max_position_embeddings": 4098,32 "model_type": "longformer",33 "num_attention_heads": 12,34 "num_hidden_layers": 12,35 "onnx_export": false,36 "output_past": true,37 "pad_token_id": 1,38 "position_embedding_type": "absolute",39 "sep_token_id": 2,40 "torch_dtype": "float32",41 "transformers_version": "4.25.0.dev0",42 "type_vocab_size": 10,43 "use_cache": true,44 "vocab_size": 5141645}46 