| { | |
| "_name_or_path": "checkpoints/de-experiments/xor-retrieve-english-span-mt5-mss-distill-unsupervised-parallel-augmentation-ICL-mss-en-anchor-pretrain-nq/checkpoint-best", | |
| "architectures": [ | |
| "RRForConditionalGeneration" | |
| ], | |
| "barlow_twins": false, | |
| "d_ff": 2816, | |
| "d_kv": 64, | |
| "d_model": 1024, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "mt5", | |
| "n_passages": 100, | |
| "num_decoder_layers": 24, | |
| "num_heads": 16, | |
| "num_layers": 24, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "retriever_layer": 12, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.30.2", | |
| "use_cache": true, | |
| "vocab_size": 250112 | |
| } | |