Model upload

README.md

@@ -1,3 +1,67 @@
 ---
+language:
+- multilingual
+- pl
+- ru
+- uk
+- bg
+- cs
+- sl
+datasets:
+- SlavicNER
 license: apache-2.0
+library_name: transformers
+pipeline_tag: text2text-generation
+tags:
+- lemmatization
+widget:
+  - text: "pl:Polsce"
+  - text: "cs:Velké Británii"
+  - text: "bg:българите"
+  - text: "ru:Великобританию"
+  - text: "sl:evropske komisije"
+  - text: "uk:Європейського агентства лікарських засобів"
 ---
+
+# Model description
+
+This is a baseline model for named entity **lemmatization** trained on the single-out topic split of the 
+[SlavicNER corpus](https://github.com/SlavicNLP/SlavicNER).
+
+
+# Resources and Technical Documentation
+
+- Paper: [Cross-lingual Named Entity Corpus for Slavic Languages](https://arxiv.org/pdf/2404.00482), to appear in LREC-COLING 2024.
+- Annotation guidelines: https://arxiv.org/pdf/2404.00482
+- SlavicNER Corpus: https://github.com/SlavicNLP/SlavicNER
+
+
+# Evaluation
+
+*Will appear soon*
+
+
+# Usage
+
+You can use this model directly with a pipeline for text2text generation:
+
+```python
+from transformers import pipeline
+
+model_name = "SlavicNLP/slavicner-lemma-cross-topic-large"
+pipe = pipeline("text2text-generation", model_name)
+
+texts = ["pl:Polsce", "cs:Velké Británii", "bg:българите", "ru:Великобританию",
+         "sl:evropske komisije", "uk:Європейського агентства лікарських засобів"]
+
+outputs = pipe(texts)
+
+ids = [o['generated_text'] for o in outputs]
+print(ids)
+# ['GPE-Poland', 'GPE-Great-Britain', 'GPE-Bulgaria', 'GPE-Great-Britain',
+#  'ORG-European-Commission', 'ORG-EMA-European-Medicines-Agency']
+```
+
+# Citation
+
+*Will appear soon*

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/mt5-large",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0fca9e2a1b1ffddf8e8462f737b2c9303f65c176f4a590752e42f0648b11a77
+size 4918393736

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "extra_ids": 0,
+  "additional_special_tokens": null,
+  "tokenizer_file": null,
+  "name_or_path": "google/mt5-small"
+}