lordtt13 commited on
Commit
6a2ff12
1 Parent(s): 0328a02

Add blenderbot_small-news

Browse files

Signed-off-by: lordtt13 <[email protected]>

config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "blenderbot_small-news/",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BlenderbotSmallForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 1,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 512,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 2048,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 8,
19
+ "decoder_start_token_id": 1,
20
+ "do_blenderbot_90_layernorm": true,
21
+ "dropout": 0.1,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 2048,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 8,
26
+ "eos_token_id": 2,
27
+ "extra_pos_embeddings": 0,
28
+ "force_bos_token_to_be_generated": false,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "layernorm_variant": "xlm",
43
+ "length_penalty": 0.65,
44
+ "max_length": 128,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 20,
47
+ "model_type": "blenderbot-small",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "normalize_embedding": true,
51
+ "num_beams": 10,
52
+ "num_hidden_layers": 8,
53
+ "pad_token_id": 0,
54
+ "scale_embedding": true,
55
+ "static_position_embeddings": false,
56
+ "transformers_version": "4.2.2",
57
+ "unk_token_id": 3,
58
+ "use_cache": true,
59
+ "vocab_size": 54944
60
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1bdea92c0ce998be3267dd304c6a2e2b6065b7470b3157f94d77226c0ac406
3
+ size 350391879
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "__start__", "eos_token": "__end__", "unk_token": "__unk__", "pad_token": "__null__"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:103acc81f21b9ac555171742dd41f5f75f45bcb54803ff9e890bcdd5fc2a1ed1
3
+ size 350399296
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "__unk__", "bos_token": "__start__", "eos_token": "__end__", "pad_token": "__null__", "model_max_length": 512, "name_or_path": "facebook/blenderbot_small-90M"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15730c0f1359738150786e9f21f8f7db1f98d2db7a0ad57f77a24ff294c9b065
3
+ size 2031
vocab.json ADDED
The diff for this file is too large to render. See raw diff