IDEA-CCNL/Randeng-T5-784M-MultiTask-Chinese
75145
1{2 "_name_or_path": "/cognitive_comp/wuxiaojun/pretrained/pytorch/Randeng-T5-784M",3 "architectures": [4 "T5ForConditionalGeneration"5 ],6 "d_ff": 2816,7 "d_kv": 64,8 "d_model": 1024,9 "decoder_start_token_id": 0,10 "dropout_rate": 0.1,11 "eos_token_id": 1,12 "feed_forward_proj": "gated-gelu",13 "initializer_factor": 1.0,14 "is_encoder_decoder": true,15 "layer_norm_epsilon": 1e-06,16 "max_length": 200,17 "model_type": "t5",18 "num_decoder_layers": 24,19 "num_heads": 16,20 "num_layers": 24,21 "output_past": true,22 "pad_token_id": 0,23 "relative_attention_max_distance": 128,24 "relative_attention_num_buckets": 32,25 "tie_word_embeddings": false,26 "tokenizer_class": "T5Tokenizer",27 "torch_dtype": "float32",28 "transformers_version": "4.18.0",29 "use_cache": true,30 "vocab_size": 3259631}32 