mirror
/
zippy
kopia lustrzana https://github.com/thinkst/zippy
1
0
Forkuj 0
Kod Zgłoszenia Packages Projekty Wydania Wiki Aktywność

Remove unstructured GPT-2 testcases 

Signed-off-by: Jacob Torrey <jacob@thinkst.com>
pull/6/head
Jacob Torrey 2023-05-24 15:23:06 -06:00
rodzic d1e689801b
commit 2179778dcf
1 zmienionych plików z 11 dodań i 11 usunięć
Pokaż statystyki Ściągnij plik aktualizacji Ściągnij plik porównania Expand all files Collapse all files

22
test_lzma_detect.py
Wyświetl plik

@ -60,18 +60,18 @@ def test_human_jsonl(i, record_property):
record_property("score", str(score))
assert classification == 'Human', HUMAN_JSONL_FILE + ':' + str(i.get('id')) + ' (len: ' + str(i.get('length', -1)) + ') is a human-generated sample, misclassified as AI-generated with confidence ' + str(round(score, 8))
AI_JSONL_FILE = 'samples/xl-1542M.test.jsonl'
ai_samples = []
with jsonlines.open(AI_JSONL_FILE) as reader:
for obj in reader:
if obj.get('length', 0) >= MIN_LEN:
ai_samples.append(obj)
# AI_JSONL_FILE = 'samples/xl-1542M.test.jsonl'
# ai_samples = []
# with jsonlines.open(AI_JSONL_FILE) as reader:
# for obj in reader:
# if obj.get('length', 0) >= MIN_LEN:
# ai_samples.append(obj)
@pytest.mark.parametrize('i', ai_samples[0:NUM_JSONL_SAMPLES])
def test_gpt2_jsonl(i, record_property):
(classification, score) = run_on_text_chunked(i.get('text', ''), fuzziness=FUZZINESS, prelude_ratio=PRELUDE_RATIO)
record_property("score", str(score))
assert classification == 'AI', AI_JSONL_FILE + ':' + str(i.get('id')) + ' (text: ' + i.get('text', "").replace('\n', ' ')[:50] + ') is an LLM-generated sample, misclassified as human-generated with confidence ' + str(round(score, 8))
# @pytest.mark.parametrize('i', ai_samples[0:NUM_JSONL_SAMPLES])
# def test_gpt2_jsonl(i, record_property):
# (classification, score) = run_on_text_chunked(i.get('text', ''), fuzziness=FUZZINESS, prelude_ratio=PRELUDE_RATIO)
# record_property("score", str(score))
# assert classification == 'AI', AI_JSONL_FILE + ':' + str(i.get('id')) + ' (text: ' + i.get('text', "").replace('\n', ' ')[:50] + ') is an LLM-generated sample, misclassified as human-generated with confidence ' + str(round(score, 8))
GPT3_JSONL_FILE = 'samples/GPT-3-175b_samples.jsonl'
gpt3_samples = []