mtasic85 commited on
Commit
cbbac33
1 Parent(s): 1816ac6

pretrain model

Browse files
scripts/prepare_pretrain_dataset.py CHANGED
@@ -222,7 +222,7 @@ datasets_names = [
222
  'm-a-p/CodeFeedback-Filtered-Instruction',
223
  'jtatman/python-code-dataset-500k',
224
  'iamtarun/python_code_instructions_18k_alpaca',
225
- '',
226
  'gair-prox/open-web-math-pro',
227
  'ajibawa-2023/Maths-College',
228
  'microsoft/orca-math-word-problems-200k',
 
222
  'm-a-p/CodeFeedback-Filtered-Instruction',
223
  'jtatman/python-code-dataset-500k',
224
  'iamtarun/python_code_instructions_18k_alpaca',
225
+ 'HuggingFaceH4/CodeAlpaca_20K',
226
  'gair-prox/open-web-math-pro',
227
  'ajibawa-2023/Maths-College',
228
  'microsoft/orca-math-word-problems-200k',