Merge branch 'main' of https://huggingface.co/flax-community/roberta-base-danish into main

.gitignore

@@ -0,0 +1,134 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# VIm
+**/.vim
+**/.swp
+**/.swo

README.md

@@ -18,4 +18,4 @@ This is a sample reference model for Flax/Jax training using only on the MC4. It
 
 ---
 ## Description
-My description
+My description

config.json

@@ -24,4 +24,4 @@
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265
-}
+}

continue_run_mlm_flax_stream.sh

@@ -23,4 +23,4 @@ python3 ./src/run_mlm_flax_stream.py \
     --eval_steps="1000" \
     #--push_to_hub \
     #--config_name="${MODEL_DIR}" \
-    #--model_type="roberta" \
+    #--model_type="roberta" \

md_logs/train_tokenizer.md

@@ -67,4 +67,4 @@ python3 train_tokenizer.py
 ### Problems while developing the script:
 -  Loading the '*mc4*' dataset using the  `load_dataset()` from HugginFace's dataset package `datasets` was not able to load multiple language in one line of code, as otherwise specified [here](https://huggingface.co/datasets/mc4). It was thus chosen to load each language and concatenate them.
 - Furthermore, it seems that even though you predefine a subset-split using the `split` argument, the entire dataset still needs to be downloaded. 
-- Some bug occured when downloading the danish dataset, and we then had to force a redownload to mitigate the bug, and make the VM download it. 
+- Some bug occured when downloading the danish dataset, and we then had to force a redownload to mitigate the bug, and make the VM download it. 

special_tokens_map.json

@@ -1 +1,15 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
+{
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "sep_token": "</s>",
+    "pad_token": "<pad>",
+    "cls_token": "<s>",
+    "mask_token": {
+        "content": "<mask>",
+        "single_word": false,
+        "lstrip": true,
+        "rstrip": false,
+        "normalized": false
+    }
+}

tokenizer_config.json

@@ -1 +1,14 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "RobertaTokenizer"}
+{
+    "unk_token": "<unk>",
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "add_prefix_space": false,
+    "errors": "replace",
+    "sep_token": "</s>",
+    "cls_token": "<s>",
+    "pad_token": "<pad>",
+    "mask_token": "<mask>",
+    "special_tokens_map_file": null,
+    "name_or_path": "./",
+    "tokenizer_class": "RobertaTokenizer"
+}