mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-07 02:59:05 +00:00
fix sagemaker tests
This commit is contained in:
parent
0d374fb7c0
commit
40dc27e72c
1 changed files with 0 additions and 75 deletions
|
|
@ -3337,81 +3337,6 @@ def test_customprompt_together_ai():
|
|||
# test_customprompt_together_ai()
|
||||
|
||||
|
||||
# test_completion_sagemaker()
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="AWS Suspended Account")
|
||||
@pytest.mark.asyncio
|
||||
async def test_acompletion_sagemaker():
|
||||
try:
|
||||
litellm.set_verbose = True
|
||||
print("testing sagemaker")
|
||||
response = await litellm.acompletion(
|
||||
model="sagemaker/jumpstart-dft-hf-llm-mistral-7b-ins-20240329-150233",
|
||||
model_id="huggingface-llm-mistral-7b-instruct-20240329-150233",
|
||||
messages=messages,
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
aws_region_name=os.getenv("AWS_REGION_NAME_2"),
|
||||
aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID_2"),
|
||||
aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY_2"),
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
print(response)
|
||||
cost = completion_cost(completion_response=response)
|
||||
print("calculated cost", cost)
|
||||
assert (
|
||||
cost > 0.0 and cost < 1.0
|
||||
) # should never be > $1 for a single completion call
|
||||
except Exception as e:
|
||||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="AWS Suspended Account")
|
||||
def test_completion_chat_sagemaker():
|
||||
try:
|
||||
messages = [{"role": "user", "content": "Hey, how's it going?"}]
|
||||
litellm.set_verbose = True
|
||||
response = completion(
|
||||
model="sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4",
|
||||
messages=messages,
|
||||
max_tokens=100,
|
||||
temperature=0.7,
|
||||
stream=True,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
complete_response = ""
|
||||
for chunk in response:
|
||||
complete_response += chunk.choices[0].delta.content or ""
|
||||
print(f"complete_response: {complete_response}")
|
||||
assert len(complete_response) > 0
|
||||
except Exception as e:
|
||||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
# test_completion_chat_sagemaker()
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="AWS Suspended Account")
|
||||
def test_completion_chat_sagemaker_mistral():
|
||||
try:
|
||||
messages = [{"role": "user", "content": "Hey, how's it going?"}]
|
||||
|
||||
response = completion(
|
||||
model="sagemaker/jumpstart-dft-hf-llm-mistral-7b-instruct",
|
||||
messages=messages,
|
||||
max_tokens=100,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
print(response)
|
||||
except Exception as e:
|
||||
pytest.fail(f"An error occurred: {str(e)}")
|
||||
|
||||
|
||||
# test_completion_chat_sagemaker_mistral()
|
||||
|
||||
|
||||
def response_format_tests(response: litellm.ModelResponse):
|
||||
assert isinstance(response.id, str)
|
||||
assert response.id != ""
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue