| { | |
| "_name_or_path": "/exports/eddie/scratch/s1970716/models/longt5_xl_sfd_bp_15/checkpoint-210/", | |
| "architectures": [ | |
| "LongT5ForConditionalGeneration" | |
| ], | |
| "d_ff": 5120, | |
| "d_kv": 64, | |
| "d_model": 2048, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "encoder_attention_type": "transient-global", | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "global_block_size": 16, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "local_radius": 127, | |
| "model_type": "longt5", | |
| "n_positions": 4096, | |
| "num_decoder_layers": 24, | |
| "num_heads": 32, | |
| "num_layers": 24, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.1", | |
| "use_cache": true, | |
| "vocab_size": 32128 | |
| } | |