multimolecule/progen2-medium

1{2  "architectures": [3    "ProGen2ForPreTraining"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 1,7  "dtype": "float32",8  "embedding_dropout": 0.0,9  "eos_token_id": 2,10  "gradient_checkpointing": false,11  "hidden_act": "gelu_new",12  "hidden_dropout": 0.0,13  "hidden_size": 1536,14  "id2label": null,15  "initializer_range": 0.02,16  "intermediate_size": 6144,17  "is_decoder": true,18  "label2id": null,19  "layer_norm_eps": 1e-05,20  "mask_token_id": 4,21  "max_position_embeddings": 1024,22  "model_type": "progen2",23  "null_token_id": null,24  "num_attention_heads": 16,25  "num_hidden_layers": 27,26  "num_labels": 1,27  "pad_token_id": 0,28  "rotary_dim": 48,29  "scale_attn_weights": true,30  "summary_activation": null,31  "summary_first_dropout": 0.1,32  "summary_proj_to_labels": true,33  "summary_type": "cls_index",34  "summary_use_proj": true,35  "task_specific_params": {36    "text-generation": {37      "do_sample": true,38      "max_length": 50,39      "temperature": 1.040    }41  },42  "tie_word_embeddings": false,43  "tokenizer_class": "GPT2Tokenizer",44  "transformers_version": "5.9.0",45  "unk_token_id": 3,46  "use_cache": true,47  "vocab_size": 3748}49