bigscience/mt0-small
325.3k
1{2 "_name_or_path": "google/mt5-small",3 "architectures": [4 "MT5ForConditionalGeneration"5 ],6 "d_ff": 1024,7 "d_kv": 64,8 "d_model": 512,9 "decoder_start_token_id": 0,10 "dense_act_fn": "gelu_new",11 "dropout_rate": 0.1,12 "eos_token_id": 1,13 "feed_forward_proj": "gated-gelu",14 "initializer_factor": 1.0,15 "is_encoder_decoder": true,16 "is_gated_act": true,17 "layer_norm_epsilon": 1e-06,18 "model_type": "mt5",19 "num_decoder_layers": 8,20 "num_heads": 6,21 "num_layers": 8,22 "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": "4.23.1",29 "use_cache": true,30 "vocab_size": 25011231}32 