Merge branch 'main' of https://huggingface.co/krotima1/mbart-at2h-s into main

README.md

@@ -0,0 +1,62 @@
+---
+language:
+- cs
+- cs
+tags:
+- abstractive summarization
+- mbart-cc25
+- Czech
+license: apache-2.0
+datasets:
+- SumeCzech dataset news-based
+metrics:
+- rouge
+- rougeraw
+---
+
+# mBART fine-tuned model for Czech abstractive summarization (AT2H-S)
+This model is a fine-tuned checkpoint of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) on the Czech news dataset to produce Czech abstractive summaries.
+## Task
+The model deals with the task ``Abstract + Text to Headline`` (AT2H) which consists in generating a one- or two-sentence summary considered as a headline from a Czech news text.
+
+## Dataset
+The model has been trained on the [SumeCzech](https://ufal.mff.cuni.cz/sumeczech) dataset. The dataset includes around 1M Czech news-based documents consisting of a Headline, Abstract, and Full-text sections. Truncation and padding were configured for 512 tokens for the encoder and 64 for the decoder.
+
+## Training
+The model has been trained on 1x NVIDIA Tesla A100 40GB for 40 hours. During training, the model has seen 2576K documents corresponding to roughly 3 epochs.
+
+# Use
+Assuming you are using the provided Summarizer.ipynb file.
+```python
+def summ_config():
+    cfg = OrderedDict([
+        # summarization model - checkpoint from website
+        ("model_name", "krotima1/mbart-at2h-s"),
+        ("inference_cfg", OrderedDict([
+            ("num_beams", 4),
+            ("top_k", 40),
+            ("top_p", 0.92),
+            ("do_sample", True),
+            ("temperature", 0.89),
+            ("repetition_penalty", 1.2),
+            ("no_repeat_ngram_size", None),
+            ("early_stopping", True),
+            ("max_length", 64),
+            ("min_length", 10),
+        ])),
+        #texts to summarize
+        ("text",
+            [
+                "Input your Czech text",
+            ]
+        ),
+    ])
+    return cfg
+cfg = summ_config()
+#load model    
+model = AutoModelForSeq2SeqLM.from_pretrained(cfg["model_name"])
+tokenizer = AutoTokenizer.from_pretrained(cfg["model_name"])
+# init summarizer
+summarize = Summarizer(model, tokenizer, cfg["inference_cfg"])
+summarize(cfg["text"])
+```