Upload polemma-base

README.md

@@ -1,3 +1,50 @@
 ---
+language: pl
+tags:
+  - T5
+  - lemmatization
 license: apache-2.0
 ---
+
+
+# PoLemma Base
+
+PoLemma models are intended for lemmatization of named entities and multi-word expressions in the Polish language.
+
+They were fine-tuned from the allegro/plT5 models, e.g.: [allegro/plt5-base](https://huggingface.co/allegro/plt5-base).
+
+## Usage
+
+Sample usage:
+
+```
+from transformers import pipeline
+
+pipe = pipeline(task="text2text-generation", model="amu-cai/polemma-base", tokenizer="amu-cai/polemma-base")
+hyp = [res['generated_text'] for res in pipe(["wytrenowanego modelu"], clean_up_tokenization_spaces=True, num_beams=5)][0]
+```
+
+
+## Evaluation results
+
+Lemmatization Exact Match was computed on the SlavNER 2021 test set.
+
+| Model | Exact Match ||
+| :------ | ------: | ------: |
+| [polemma-large]() | 92.61  | 
+| [polemma-base]() | 91.34  |
+| [polemma-small]()| 88.46 |
+
+
+## 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": "allegro/plt5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "t5",
+  "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": 50048
+}

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 sha256:7835279333d28fbabe73f1f5a75f64baac7357a57efd1d2b7e46d4c2f85de37e
+size 1100509365

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:a200b4b9d7106b32ea2340e5cd27033a5c03ae5ece9241ab6e1f685b938800b9
+size 1124950

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "allegro/plt5-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/wmi/.cache/huggingface/hub/models--allegro--plt5-base/snapshots/56379680948ce8b42d3d48df86569cfc210d3060/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}