Update config.json
Browse files- config.json +3 -38
config.json
CHANGED
@@ -1,69 +1,34 @@
|
|
1 |
{
|
2 |
-
"_num_labels": 2,
|
3 |
"architectures": [
|
4 |
"ReformerModelWithLMHead"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.3,
|
7 |
-
"bad_words_ids": null,
|
8 |
-
"bos_token_id": null,
|
9 |
"chunk_length": 7,
|
10 |
"chunk_size_feed_forward": 0,
|
11 |
"chunk_size_lm_head": 0,
|
12 |
"d_ff": 128,
|
13 |
"d_model": 128,
|
14 |
-
"decoder_start_token_id": null,
|
15 |
-
"do_sample": false,
|
16 |
-
"early_stopping": false,
|
17 |
-
"eos_token_id": null,
|
18 |
"feed_forward_size": 128,
|
19 |
"ff_chunk_size": 0,
|
20 |
-
"finetuning_task": null,
|
21 |
"hidden_act": "gelu",
|
22 |
"hidden_dropout_prob": 0.3,
|
23 |
"hidden_size": 128,
|
24 |
-
"id2label": {
|
25 |
-
"0": "LABEL_0",
|
26 |
-
"1": "LABEL_1"
|
27 |
-
},
|
28 |
"initializer_range": 0.02,
|
29 |
-
"
|
30 |
-
"is_encoder_decoder": false,
|
31 |
-
"label2id": {
|
32 |
-
"LABEL_0": 0,
|
33 |
-
"LABEL_1": 1
|
34 |
-
},
|
35 |
"layer_norm_eps": 1e-12,
|
36 |
-
"length_penalty": 1.0,
|
37 |
-
"max_length": 20,
|
38 |
"max_position_embeddings": 512,
|
39 |
-
"min_length": 0,
|
40 |
"model_type": "bert",
|
41 |
-
"no_repeat_ngram_size": 0,
|
42 |
"num_attention_chunks": 1,
|
43 |
"num_attention_heads": 2,
|
44 |
-
"num_beams": 1,
|
45 |
"num_buckets": 2,
|
46 |
"num_chunks": 0,
|
47 |
"num_chunks_after": 0,
|
48 |
"num_chunks_before": 1,
|
49 |
"num_hashes": 4,
|
50 |
"num_hidden_layers": 3,
|
51 |
-
"num_return_sequences": 1,
|
52 |
-
"output_attentions": false,
|
53 |
-
"output_hidden_states": false,
|
54 |
"output_past": true,
|
55 |
-
"pad_token_id": null,
|
56 |
-
"prefix": null,
|
57 |
-
"pruned_heads": {},
|
58 |
-
"repetition_penalty": 1.0,
|
59 |
"seed": 0,
|
60 |
"sinusoidal_pos_embds": true,
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"top_k": 50,
|
64 |
-
"top_p": 1.0,
|
65 |
-
"torchscript": false,
|
66 |
-
"use_bfloat16": false,
|
67 |
-
"vocab_size": 200,
|
68 |
-
"xla_device": null
|
69 |
}
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"ReformerModelWithLMHead"
|
4 |
],
|
5 |
"attention_probs_dropout_prob": 0.3,
|
|
|
|
|
6 |
"chunk_length": 7,
|
7 |
"chunk_size_feed_forward": 0,
|
8 |
"chunk_size_lm_head": 0,
|
9 |
"d_ff": 128,
|
10 |
"d_model": 128,
|
|
|
|
|
|
|
|
|
11 |
"feed_forward_size": 128,
|
12 |
"ff_chunk_size": 0,
|
|
|
13 |
"hidden_act": "gelu",
|
14 |
"hidden_dropout_prob": 0.3,
|
15 |
"hidden_size": 128,
|
|
|
|
|
|
|
|
|
16 |
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
|
|
|
|
|
|
|
|
|
|
18 |
"layer_norm_eps": 1e-12,
|
|
|
|
|
19 |
"max_position_embeddings": 512,
|
|
|
20 |
"model_type": "bert",
|
|
|
21 |
"num_attention_chunks": 1,
|
22 |
"num_attention_heads": 2,
|
|
|
23 |
"num_buckets": 2,
|
24 |
"num_chunks": 0,
|
25 |
"num_chunks_after": 0,
|
26 |
"num_chunks_before": 1,
|
27 |
"num_hashes": 4,
|
28 |
"num_hidden_layers": 3,
|
|
|
|
|
|
|
29 |
"output_past": true,
|
|
|
|
|
|
|
|
|
30 |
"seed": 0,
|
31 |
"sinusoidal_pos_embds": true,
|
32 |
+
"type_vocab_size": 2,
|
33 |
+
"vocab_size": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|