make sure chatml dpo dataset loading works (#2333)

This commit is contained in:
Wing Lian
2025-02-18 16:08:40 -05:00
committed by GitHub
parent c3d4f6e295
commit 23a9fcb0a7
2 changed files with 67 additions and 0 deletions

View File

@@ -125,6 +125,12 @@ def fixture_llama3_tokenizer():
return tokenizer
@pytest.fixture(name="smollm2_tokenizer", scope="session", autouse=True)
def fixture_smollm2_tokenizer():
tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-135M")
return tokenizer
@pytest.fixture(name="mistralv03_tokenizer", scope="session", autouse=True)
def fixture_mistralv03_tokenizer():
tokenizer = AutoTokenizer.from_pretrained(