adibvafa/CodonTransformer-base
1312
1{
2 "architectures": [
3 "BigBirdForMaskedLM"
4 ],
5 "attention_probs_dropout_prob": 0.1,
6 "attention_type": "block_sparse",
7 "block_size": 64,
8 "bos_token_id": 1,
9 "classifier_dropout": null,
10 "eos_token_id": 2,
11 "hidden_act": "gelu_new",
12 "hidden_dropout_prob": 0.1,
13 "hidden_size": 768,
14 "initializer_range": 0.02,
15 "intermediate_size": 3072,
16 "layer_norm_eps": 1e-12,
17 "max_position_embeddings": 4096,
18 "model_type": "big_bird",
19 "num_attention_heads": 12,
20 "num_hidden_layers": 12,
21 "num_random_blocks": 3,
22 "pad_token_id": 0,
23 "rescale_embeddings": false,
24 "sep_token_id": 2,
25 "torch_dtype": "float32",
26 "transformers_version": "4.40.0",
27 "type_vocab_size": 164,
28 "use_bias": true,
29 "use_cache": true,
30 "vocab_size": 90
31}
32 