balastml/COPAL
037
1{
2 "architectures": [
3 "T5ForConditionalGeneration"
4 ],
5 "classifier_dropout": 0.0,
6 "d_ff": 3072,
7 "d_kv": 64,
8 "d_model": 768,
9 "decoder_start_token_id": 0,
10 "dense_act_fn": "relu",
11 "dropout_rate": 0.1,
12 "dtype": "float32",
13 "eos_token_id": 1,
14 "feed_forward_proj": "relu",
15 "initializer_factor": 1.0,
16 "is_decoder": false,
17 "is_encoder_decoder": true,
18 "is_gated_act": false,
19 "layer_norm_epsilon": 1e-06,
20 "model_type": "t5",
21 "n_positions": 512,
22 "num_decoder_layers": 12,
23 "num_heads": 12,
24 "num_layers": 12,
25 "output_past": true,
26 "pad_token_id": 0,
27 "relative_attention_max_distance": 128,
28 "relative_attention_num_buckets": 32,
29 "scale_decoder_outputs": true,
30 "tie_word_embeddings": true,
31 "transformers_version": "5.12.1",
32 "use_cache": true,
33 "vocab_size": 32128
34}
35 