Update README.md

README.md

@@ -10,6 +10,45 @@ part of the wiki40b dataset.
 
 https://huggingface.co/datasets/wiki40b
 
+## Model series
+This model is part of a series of models training on TPU with Flax Jax during Huggingface Flax/Jax challenge.
+
+## Gpt models
+
+## Swedish Gpt
+https://huggingface.co/birgermoell/swedish-gpt/
+
+## Swedish gpt wiki
+https://huggingface.co/flax-community/swe-gpt-wiki
+
+# Nordic gpt wiki
+https://huggingface.co/flax-community/nordic-gpt-wiki
+
+## Dansk gpt wiki
+https://huggingface.co/flax-community/dansk-gpt-wiki
+
+## Norsk gpt wiki
+https://huggingface.co/flax-community/norsk-gpt-wiki
+
+## Roberta models
+
+## Nordic Roberta Wiki
+https://huggingface.co/flax-community/nordic-roberta-wiki
+
+## Swe Roberta Wiki Oscar
+https://huggingface.co/flax-community/swe-roberta-wiki-oscar
+
+## Roberta Swedish Scandi
+https://huggingface.co/birgermoell/roberta-swedish-scandi
+
+## Roberta Swedish
+https://huggingface.co/birgermoell/roberta-swedish
+
+## Swedish T5 model
+https://huggingface.co/birgermoell/t5-base-swedish
+
+
+
 
 ## Data cleaning and preprocessing
 The data was cleaned and preprocessed using the following script. Make sure to install depencies for beam_runner to make the dataset work.
@@ -26,10 +65,18 @@ def load_and_clean_wiki():
     return filtered_dataset
 
 def filter_wikipedia(batch):
-    batch["text"] = " ".join(batch["text"].split("\n_START_SECTION_\n"))
-    batch["text"] = " ".join(batch["text"].split("\n_START_ARTICLE_\n"))
-    batch["text"] = " ".join(batch["text"].split("\n_START_ARTICLE_\n"))
-    batch["text"] = " ".join(batch["text"].split("\n_START_PARAGRAPH_\n"))
+    batch["text"] = " ".join(batch["text"].split("\
+_START_SECTION_\
+"))
+    batch["text"] = " ".join(batch["text"].split("\
+_START_ARTICLE_\
+"))
+    batch["text"] = " ".join(batch["text"].split("\
+_START_ARTICLE_\
+"))
+    batch["text"] = " ".join(batch["text"].split("\
+_START_PARAGRAPH_\
+"))
     batch["text"] = " ".join(batch["text"].split("_NEWLINE_"))
     batch["text"] = " ".join(batch["text"].split("\xa0"))
     return batch