config.json
766 B · 33 lines · json Raw
1 {
2 "_name_or_path": "cointegrated/rut5-base",
3 "architectures": [
4 "T5ForConditionalGeneration"
5 ],
6 "bos_token_id": 2,
7 "d_ff": 2048,
8 "d_kv": 64,
9 "d_model": 768,
10 "decoder_start_token_id": 2,
11 "dropout_rate": 0.1,
12 "eos_token_id": 1,
13 "feed_forward_proj": "gated-gelu",
14 "initializer_factor": 1.0,
15 "is_encoder_decoder": true,
16 "layer_norm_epsilon": 1e-06,
17 "max_length": 100,
18 "model_type": "t5",
19 "num_beams": 5,
20 "num_decoder_layers": 12,
21 "num_heads": 12,
22 "num_layers": 12,
23 "output_past": true,
24 "pad_token_id": 0,
25 "relative_attention_num_buckets": 32,
26 "tie_word_embeddings": false,
27 "tokenizer_class": "T5Tokenizer",
28 "torch_dtype": "float32",
29 "transformers_version": "4.12.5",
30 "use_cache": true,
31 "vocab_size": 30000
32 }
33