abhinavchandran/Github_Reader

1{
2  "architectures": [
3    "T5ForConditionalGeneration"
4  ],
5  "classifier_dropout": 0.0,
6  "d_ff": 2048,
7  "d_kv": 64,
8  "d_model": 512,
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": 6,
23  "num_heads": 8,
24  "num_layers": 6,
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  "task_specific_params": {
31    "summarization": {
32      "early_stopping": true,
33      "length_penalty": 2.0,
34      "max_length": 200,
35      "min_length": 30,
36      "no_repeat_ngram_size": 3,
37      "num_beams": 4,
38      "prefix": "summarize: "
39    },
40    "translation_en_to_de": {
41      "early_stopping": true,
42      "max_length": 300,
43      "num_beams": 4,
44      "prefix": "translate English to German: "
45    },
46    "translation_en_to_fr": {
47      "early_stopping": true,
48      "max_length": 300,
49      "num_beams": 4,
50      "prefix": "translate English to French: "
51    },
52    "translation_en_to_ro": {
53      "early_stopping": true,
54      "max_length": 300,
55      "num_beams": 4,
56      "prefix": "translate English to Romanian: "
57    }
58  },
59  "tie_word_embeddings": true,
60  "transformers_version": "5.13.1",
61  "use_cache": false,
62  "vocab_size": 32128
63}
64