upload slavlemma-base

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,64 @@
 ---
+language: 
+  - pl
+  - cs
+  - ru
+tags:
+  - mT5
+  - lemmatization
 license: apache-2.0
 ---
+
+
+# SlavLemma Base
+
+SlavLemma models are intended for lemmatization of named entities and multi-word expressions in Polish, Czech and Russian languages.
+
+They were fine-tuned from the google/mT5 models, e.g.: [google/mt5-base](https://huggingface.co/google/mt5-base).
+
+## Usage
+
+When using the model, prepend one of the language tokens (`>>pl<<`, `>>cs<<`, `>>ru<<`) to the input, based on the language of the phrase you want to lemmatize.
+
+Sample usage:
+
+```
+from transformers import pipeline
+
+pipe = pipeline(task="text2text-generation", model="amu-cai/slavlemma-base", tokenizer="amu-cai/slavlemma-base")
+hyp = [res['generated_text'] for res in pipe([">>pl<< federalnego urzędu statystycznego"], clean_up_tokenization_spaces=True, num_beams=5)][0]
+```
+
+
+## Evaluation results
+
+Lemmatization Exact Match was computed on the SlavNER 2021 test sets (COVID-19 and USA 2020 Elections).
+
+
+COVID-19:
+| Model | pl | cs | ru |
+| :------ | ------: | ------: | ------: |
+| [slavlemma-large](https://huggingface.co/amu-cai/slavlemma-large) | 93.76 | 89.80 | 77.30
+| [slavlemma-base](https://huggingface.co/amu-cai/slavlemma-base) | 91.00 |86.29| 76.10
+| [slavlemma-small](https://huggingface.co/amu-cai/slavlemma-small)| 86.80 |80.98| 73.83
+
+USA 2020 Elections:
+| Model | pl | cs | ru |
+| :------ | ------: | ------: | ------: |
+| [slavlemma-large](https://huggingface.co/amu-cai/slavlemma-large) | 89.12 | 87.27| 82.50
+| [slavlemma-base](https://huggingface.co/amu-cai/slavlemma-base) | 84.19 |81.97| 80.27
+| [slavlemma-small](https://huggingface.co/amu-cai/slavlemma-small)| 78.85 |75.86| 76.18
+
+
+## Citation
+
+If you use the model, please cite the following paper:
+
+TBD
+
+### Framework versions
+
+- Transformers 4.26.0
+- Pytorch 1.13.1.post200
+- Datasets 2.9.0
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53328c427c222d66b02976ad822746b073f5d2e5385ee3422109afaef447e38
+size 2329702453

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/mt5-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}