vesteinn commited on
Commit
ffd51ce
1 Parent(s): 3a8313b

Model added

Browse files
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ----
2
+ language:
3
+ - is
4
+ thumbnail:
5
+ tags:
6
+ - icelandic
7
+ - xlmr
8
+ license:
9
+ datasets:
10
+ - ic3
11
+ - igc
12
+ - books3
13
+ widget:
14
+ - text: "The capital of Iceland is<mask> ."
15
+ - text: "Höfuðborg Íslands er<mask> ."
16
+ ---
17
+
18
+ # XLMR-ENIS
19
+
20
+ ## Model description
21
+
22
+ This is a XLMR model trained on Icelandic and English text.
23
+
24
+ ## Intended uses & limitations
25
+
26
+ This model is part of my MSc thesis about Q&A for Icelandic.
27
+
28
+ #### How to use
29
+
30
+ ```python
31
+ from transformers import AutoTokenizer, AutoModelForMaskedLM
32
+
33
+ tokenizer = AutoTokenizer.from_pretrained("vesteinn/XLMR-ENIS")
34
+
35
+ model = AutoModelForQuestionAnswering.from_pretrained("vesteinn/XLMR-ENIS")
36
+ ```
37
+
38
+ #### Limitations and bias
39
+
40
+ ## Training data
41
+
42
+ ## Training procedure
43
+
44
+ ## Eval results
45
+
46
+ ### BibTeX entry and citation info
47
+
48
+ ```bibtex
49
+ ```
50
+
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.6.0.dev0",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 50005
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a578bb4b5697043cdacbba7fbc1605c8d3c7a03e73f857ebba4e3fcc76ba5e4
3
+ size 498278427
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb65eb67a28974dc307fed538cab36453dc8b0d934755dbdc54af9a9ad019cce
3
+ size 1051645
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff