Davlan commited on
Commit
eb8a4a3
1 Parent(s): cfe1f0f

adding Kinyarwanda XLM-R model

Browse files

README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Hugging Face's logo
2
+ ---
3
+ language: rw
4
+ datasets:
5
+
6
+ ---
7
+ # xlm-roberta-base-finetuned-kinyarwanda
8
+ ## Model description
9
+ **xlm-roberta-base-finetuned-kinyarwanda** is a **Kinyarwanda RoBERTa** model obtained by fine-tuning **xlm-roberta-base** model on Kinyarwanda language texts. It provides **better performance** than the XLM-RoBERTa on named entity recognition datasets.
10
+
11
+ Specifically, this model is a *xlm-roberta-base* model that was fine-tuned on Kinyarwanda corpus.
12
+ ## Intended uses & limitations
13
+ #### How to use
14
+ You can use this model with Transformers *pipeline* for masked token prediction.
15
+ ```python
16
+ >>> from transformers import pipeline
17
+ >>> unmasker = pipeline('fill-mask', model='Davlan/xlm-roberta-base-finetuned-kinyarwanda')
18
+ >>> unmasker("Twabonye ko igihe mu <mask> hazaba hari ikirango abantu bakunze")
19
+
20
+
21
+
22
+ ```
23
+ #### Limitations and bias
24
+ This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
25
+ ## Training data
26
+ This model was fine-tuned on JW300 + [KIRNEWS](https://github.com/Andrews2017/KINNEWS-and-KIRNEWS-Corpus) + [BBC Gahuza](https://www.bbc.com/gahuza)
27
+
28
+ ## Training procedure
29
+ This model was trained on a single NVIDIA V100 GPU
30
+
31
+ ## Eval results on Test set (F-score, average over 5 runs)
32
+ Dataset| XLM-R F1 | rw_roberta F1
33
+ -|-|-
34
+ [MasakhaNER](https://github.com/masakhane-io/masakhane-ner) | 73.22 | 77.76
35
+
36
+ ### BibTeX entry and citation info
37
+ By David Adelani
38
+ ```
39
+
40
+ ```
41
+
42
+
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "transformers_version": "4.4.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 250002
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841b2abf581f39e132c99e395f8af9666e443f95f0d75f7d29192544f1811a11
3
+ size 1113271890
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df86a7918313b4c74d266021bc73f8aa39c68f4474e81f1a9b972ef3063d2cc8
3
+ size 2287