| { | |
| "MSA_end": null, | |
| "MSA_filename": null, | |
| "MSA_start": null, | |
| "MSA_weight_file_name": null, | |
| "_name_or_path": "Tranception_Large", | |
| "activation_function": "squared_relu", | |
| "architectures": [ | |
| "TranceptionLMHeadModel" | |
| ], | |
| "attention_mode": "tranception", | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 1, | |
| "clustal_omega_location": null, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 2, | |
| "full_protein_length": null, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "local_batch_size": 1, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 1280, | |
| "n_head": 20, | |
| "n_inner": 5120, | |
| "n_layer": 36, | |
| "n_positions": 1024, | |
| "position_embedding": "grouped_alibi", | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "retrieval_aggregation_mode": null, | |
| "retrieval_inference_weight": 0.6, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "scoring_window": "optimal", | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "tokenizer": null, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.17.0", | |
| "use_cache": true, | |
| "vocab_size": 25 | |
| } | |