| { |
| "alphabet": "gene_prot", |
| "architectures": [ |
| "LucaGPLMForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_lucaone.LucaGPLMConfig", |
| "AutoModel": "modeling_lucaone.LucaGPLMModel", |
| "AutoModelForMaskedLM": "modeling_lucaone.LucaGPLMForMaskedLM", |
| "AutoModelForSequenceClassification": "modeling_lucaone.LucaGPLMForSequenceClassification", |
| "AutoModelForTokenClassification": "modeling_lucaone.LucaGPLMForTokenClassification", |
| "AutoTokenizer": "tokenization_lucaone.LucaGPLMTokenizer" |
| }, |
| "bos_token_id": 2, |
| "classifier_dropout_prob": 0.0, |
| "classifier_loss_reduction": "mean", |
| "classifier_loss_type": "cross_entropy", |
| "classifier_num_labels": -1, |
| "classifier_pooling_type": "value_attention", |
| "classifier_pos_weight": 1.0, |
| "classifier_weight": null, |
| "embed_scale": 1.0, |
| "eos_token_id": 3, |
| "ffn_dim": 10240, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 2560, |
| "ignore_index": -100, |
| "initializer_range": 0.02, |
| "layer_norm_eps": 1e-12, |
| "mask_token_id": 4, |
| "max_position_embeddings": 4096, |
| "model_type": "lucaone", |
| "no_position_embeddings": true, |
| "no_token_type_embeddings": false, |
| "num_attention_heads": 40, |
| "num_hidden_layers": 20, |
| "pad_token_id": 0, |
| "sep_token_id": 3, |
| "task_level": "seq_level", |
| "task_type": "embedding", |
| "tie_word_embeddings": false, |
| "token_dropout": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.41.2", |
| "type_vocab_size": 2, |
| "unk_token_id": 1, |
| "use_embed_layer_norm": false, |
| "use_last_layer_norm": true, |
| "vocab_size": 39 |
| } |
|
|
