update prompts for open orca to match the paper (#317)

fix the test for the updated system tokenizer
This commit is contained in:
Wing Lian
2023-07-22 13:49:11 -04:00
committed by GitHub
parent ff7f18d1ed
commit 3d4984b9a5
3 changed files with 26 additions and 6 deletions

View File

@@ -130,8 +130,9 @@ class InstructionWSystemPromptTokenizingStrategyTest(unittest.TestCase):
"output": "Hi! How can I help?",
}
example = strat.tokenize_prompt(sample)
assert example["input_ids"][0:3] == [1, 671, 20118] # <s>use cot
assert example["input_ids"][3] == 11889 # USER
assert example["input_ids"][0:4] == [1, 835, 2184, 29901] # "<s>### System:"
assert example["input_ids"][5:7] == [1509, 20118] # "use cot"
assert example["input_ids"][9] == 11889 # USER
if __name__ == "__main__":

View File

@@ -70,7 +70,7 @@ class AlpacaPrompterTest(unittest.TestCase):
)
)
assert "use cot" in res
assert res.startswith("use cot")
assert res.startswith("### System:")
assert "### Instruction:" not in res
assert "### Input:" not in res
assert "alpacas" in res