| { |
| "_name_or_path": "models/bygpt5-small/de", |
| "architectures": [ |
| "ByGPT5LMHeadModel" |
| ], |
| "d_ff": 3584, |
| "d_kv": 64, |
| "d_model": 1472, |
| "decoder_start_token_id": 0, |
| "dense_act_fn": "gelu_new", |
| "dropout_rate": 0.1, |
| "eos_token_id": 1, |
| "feed_forward_proj": "gated-gelu", |
| "gradient_checkpointing": false, |
| "initializer_factor": 1.0, |
| "is_decoder": true, |
| "is_encoder_decoder": false, |
| "is_gated_act": true, |
| "layer_norm_epsilon": 1e-06, |
| "model_type": "bygpt5", |
| "num_decoder_layers": 4, |
| "num_heads": 6, |
| "num_layers": 4, |
| "pad_token_id": 0, |
| "relative_attention_max_distance": 128, |
| "relative_attention_num_buckets": 32, |
| "tie_word_embeddings": false, |
| "tokenizer_class": "ByT5Tokenizer", |
| "torch_dtype": "float32", |
| "transformers_version": "4.20.0", |
| "use_cache": true, |
| "vocab_size": 384 |
| } |
|
|
