czuk commited on
Commit
7711778
1 Parent(s): b59af68

Model upload

Browse files
README.md CHANGED
@@ -1,3 +1,51 @@
1
  ---
 
 
 
 
 
 
 
 
 
 
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - multilingual
4
+ - pl
5
+ - ru
6
+ - uk
7
+ - bg
8
+ - cs
9
+ - sl
10
+ datasets:
11
+ - SlavicNER
12
  license: apache-2.0
13
+ library_name: transformers
14
+ pipeline_tag: text2text-generation
15
+ tags:
16
+ - entity linking
17
+ widget:
18
+ - text: "pl:Polsce"
19
+ - text: "cs:Velké Británii"
20
+ - text: "bg:българите"
21
+ - text: "ru:Великобританию"
22
+ - text: "sl:evropske komisije"
23
+ - text: "uk:Європейського агентства лікарських засобів"
24
  ---
25
+
26
+ # Model description
27
+
28
+ This is a baseline model for named entity **lemmatization** trained on the single-out topic split of the
29
+ [SlavicNER corpus](https://github.com/SlavicNLP/SlavicNER).
30
+
31
+
32
+ # Usage
33
+
34
+ You can use this model directly with a pipeline for text2text generation:
35
+
36
+ ```python
37
+ from transformers import pipeline
38
+
39
+ model_name = "SlavicNLP/slavicner-linking-cross-topic-large"
40
+ pipe = pipeline("text2text-generation", model_name)
41
+
42
+ texts = ["pl:Polsce", "cs:Velké Británii", "bg:българите", "ru:Великобританию",
43
+ "sl:evropske komisije", "uk:Європейського агентства лікарських засобів"]
44
+
45
+ outputs = pipe(texts)
46
+
47
+ ids = [o['generated_text'] for o in outputs]
48
+ print(ids)
49
+ # ['GPE-Poland', 'GPE-Great-Britain', 'GPE-Bulgaria', 'GPE-Great-Britain',
50
+ # 'ORG-European-Commission', 'ORG-EMA-European-Medicines-Agency']
51
+ ```
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-large",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.2",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.38.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6e49af30e1abf184c536e0d6af6ddc51515913721254a84e04abdd597167b4
3
+ size 4918393736
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "unk_token": "<unk>",
4
+ "pad_token": "<pad>",
5
+ "extra_ids": 0,
6
+ "additional_special_tokens": null,
7
+ "tokenizer_file": null,
8
+ "name_or_path": "google/mt5-small"
9
+ }