updates

make-tiny-xlm-roberta.py

@@ -33,13 +33,14 @@
 # 4. start with some pre-existing script from one of the https://huggingface.co/hf-internal-testing/ tiny model repos, e.g.
 # wget https://huggingface.co/hf-internal-testing/tiny-xlm-roberta/raw/main/make-tiny-xlm-roberta.py
 # chmod a+x ./make-tiny-xlm-roberta.py
+# mv ./make-tiny-xlm-roberta.py ./make-tiny-xlm-roberta.py
 #
 # 5. automatically rename things from the old names to new ones
 # perl -pi -e 's|MT5|XLMRoberta|g' make-tiny-xlm-roberta.py
 # perl -pi -e 's|mt5|xlm-roberta|g' make-tiny-xlm-roberta.py
 #
 # 6. edit and re-run this script while fixing it up
-# ./make-tiny-xlm-roberta.py .
+# ./make-tiny-xlm-roberta.py
 #
 # 7. add/commit/push
 # git add *
@@ -53,7 +54,7 @@
 # cd tiny-xlm-roberta
 #
 # 2. edit and re-run this script after doing whatever changes are needed
-# ./make-tiny-xlm-roberta.py .
+# ./make-tiny-xlm-roberta.py
 #
 # 3. commit/push
 # git commit -m "new tiny model"
@@ -72,12 +73,12 @@ os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
 
 mname_orig = "xlm-roberta-base"
 mname_tiny = "tiny-xlm-roberta"
-tmp_dir = f"/tmp/{mname_tiny}"
 
 ### Tokenizer
 
 # Shrink the orig vocab to keep things small
 vocab_keep_items = 5000
+tmp_dir = f"/tmp/{mname_tiny}"
 vocab_orig_path = f"{tmp_dir}/sentencepiece.bpe.model"
 vocab_short_path = f"{tmp_dir}/spiece-short.model"
 if 1: # set to 0 to skip this after running once to speed things up during tune up
@@ -143,6 +144,6 @@ tokenizer_fast_tiny.save_pretrained(".")
 readme = "README.md"
 if not os.path.exists(readme):
     with open(readme, "w") as f:
-        f.write(f"This is a tiny random {mname_tiny} model to be used for basic testing.")
+        f.write(f"This is a {mname_tiny} random model to be used for basic testing.\n")
 
 print(f"Generated {mname_tiny}")