updates

make-tiny-xlm-roberta.py

@@ -60,17 +60,11 @@
 # git commit -m "new tiny model"
 # git push
 
-from pathlib import Path
-import json
-import tempfile
 import sys
 import os
 
 from transformers import XLMRobertaTokenizer, XLMRobertaTokenizerFast, XLMRobertaConfig, XLMRobertaForCausalLM
 
-# workaround for fast tokenizer protobuffer issue, and it's much faster too!
-os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
-
 mname_orig = "xlm-roberta-base"
 mname_tiny = "tiny-xlm-roberta"
 
@@ -81,6 +75,8 @@ 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"
+# workaround for fast tokenizer protobuf issue, and it's much faster too!
+os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
 if 1: # set to 0 to skip this after running once to speed things up during tune up
     # HACK: need the sentencepiece source to get sentencepiece_model_pb2, as it doesn't get installed
     sys.path.append("../sentencepiece/python/src/sentencepiece")

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c6cf79904c41a0ee0dd56366d40b9d2762235495edc6d04693ca3f41c50052
+oid sha256:eb0bccafb4bee811f2138956ea9e94596e1bfdfc868b5364d7b678fac4b2d559
 size 4334436