christianbaluti commited on
Commit
d42c4fd
1 Parent(s): 8e08cda

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +63 -0
  2. generation_config.json +14 -0
  3. merges.txt +0 -0
  4. tokenizer_config.json +43 -0
  5. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/blenderbot_small-90M",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BlenderbotSmallForCausalLM"
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
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "layernorm_variant": "xlm",
45
+ "length_penalty": 0.65,
46
+ "max_length": 128,
47
+ "max_position_embeddings": 512,
48
+ "min_length": 20,
49
+ "model_type": "blenderbot-small",
50
+ "no_repeat_ngram_size": 3,
51
+ "normalize_before": false,
52
+ "normalize_embedding": true,
53
+ "num_beams": 10,
54
+ "num_hidden_layers": 8,
55
+ "pad_token_id": 0,
56
+ "scale_embedding": true,
57
+ "static_position_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.38.2",
60
+ "unk_token_id": 3,
61
+ "use_cache": true,
62
+ "vocab_size": 54944
63
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "length_penalty": 0.65,
8
+ "max_length": 128,
9
+ "min_length": 20,
10
+ "no_repeat_ngram_size": 3,
11
+ "num_beams": 10,
12
+ "pad_token_id": 0,
13
+ "transformers_version": "4.38.2"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "__null__",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "__start__",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "__end__",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "__unk__",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "__start__",
37
+ "clean_up_tokenization_spaces": true,
38
+ "eos_token": "__end__",
39
+ "model_max_length": 512,
40
+ "pad_token": "__null__",
41
+ "tokenizer_class": "BlenderbotSmallTokenizer",
42
+ "unk_token": "__unk__"
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff