Fill-Mask
Transformers
Safetensors
xlm-roberta
holocaust
speech
historical
ChrisBridges commited on
Commit
cb9288c
·
verified ·
1 Parent(s): 0c369a3

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +30 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +3 -0
  5. tokenizer_config.json +14 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "is_decoder": false,
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 514,
19
+ "model_type": "xlm-roberta",
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 24,
22
+ "output_past": true,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "tie_word_embeddings": true,
26
+ "transformers_version": "5.0.0",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 250002
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e776c429253b1c9397bba86d9ef87aa2a67014f16779f8fe77c732a0439e4a9
3
+ size 2240618704
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5451f31fe3f899dcd75ec2ad93f415528c9b5f58bb7a5a1c6dd5884fb56257
3
+ size 16781486
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "XLMRobertaTokenizer",
13
+ "unk_token": "<unk>"
14
+ }