mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 12:24:53 +00:00
fix: split chat and tool tests
This commit is contained in:
parent
5e888c4faa
commit
39a8261132
@ -13,7 +13,7 @@
|
||||
"usage": null
|
||||
}
|
||||
],
|
||||
"created": 1710795556,
|
||||
"created": 1712874856,
|
||||
"id": "",
|
||||
"model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
||||
"object": "text_completion",
|
42
integration-tests/models/test_chat_llama.py
Normal file
42
integration-tests/models/test_chat_llama.py
Normal file
@ -0,0 +1,42 @@
|
||||
import pytest
|
||||
import json
|
||||
|
||||
from text_generation.types import GrammarType
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def flash_llama_chat_handle(launcher):
|
||||
with launcher(
|
||||
"TinyLlama/TinyLlama-1.1B-Chat-v1.0", num_shard=2, disable_grammar_support=False
|
||||
) as handle:
|
||||
yield handle
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
async def flash_llama_chat(flash_llama_chat_handle):
|
||||
await flash_llama_chat_handle.health(300)
|
||||
return flash_llama_chat_handle.client
|
||||
|
||||
|
||||
@pytest.mark.private
|
||||
async def test_flash_llama_simple(flash_llama_chat, response_snapshot):
|
||||
response = await flash_llama_chat.chat(
|
||||
max_tokens=100,
|
||||
seed=1,
|
||||
messages=[
|
||||
{
|
||||
"role": "system",
|
||||
"content": "Youre a helpful assistant! Answer the users question best you can.",
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the weather like in Brooklyn, New York?",
|
||||
},
|
||||
],
|
||||
)
|
||||
|
||||
assert (
|
||||
response.choices[0].message.content
|
||||
== "As of today, there is a Update available for the Brooklyn, New York, area. According to the latest forecast, it's warm with high temperatures throughout the day. It's forecasted at 75°F for today and 77°F for tomorrow. However, in autumn, the weather typically changes drastically, becoming cooler and wetter. You can find the current weather forecast for the area through your local weather service. Additionally"
|
||||
)
|
||||
assert response == response_snapshot
|
@ -71,32 +71,6 @@ tools = [
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.private
|
||||
async def test_flash_llama_grammar_no_tools(
|
||||
flash_llama_grammar_tools, response_snapshot
|
||||
):
|
||||
response = await flash_llama_grammar_tools.chat(
|
||||
max_tokens=100,
|
||||
seed=1,
|
||||
messages=[
|
||||
{
|
||||
"role": "system",
|
||||
"content": "Youre a helpful assistant! Answer the users question best you can.",
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the weather like in Brooklyn, New York?",
|
||||
},
|
||||
],
|
||||
)
|
||||
|
||||
assert (
|
||||
response.choices[0].message.content
|
||||
== "As of today, there is a Update available for the Brooklyn, New York, area. According to the latest forecast, it's warm with high temperatures throughout the day. It's forecasted at 75°F for today and 77°F for tomorrow. However, in autumn, the weather typically changes drastically, becoming cooler and wetter. You can find the current weather forecast for the area through your local weather service. Additionally"
|
||||
)
|
||||
assert response == response_snapshot
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.private
|
||||
async def test_flash_llama_grammar_tools(flash_llama_grammar_tools, response_snapshot):
|
||||
|
Loading…
Reference in New Issue
Block a user