yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-12-26 14:38:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use Phi isntead (#8982)

Browse Source
This commit is contained in:
Sebastian Husch Lee 2025-03-05 15:53:26 +01:00 committed by GitHub
parent f741df88df
commit 4a87ceb0ed
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
test/components/generators/chat/test_hugging_face_api.py
View File

@ -570,7 +570,7 @@ class TestHuggingFaceAPIChatGenerator:
def test_live_run_serverless(self):
generator = HuggingFaceAPIChatGenerator(
api_type=HFGenerationAPIType.SERVERLESS_INFERENCE_API,
api_params={"model": "mistralai/Mistral-7B-Instruct-v0.3"},
api_params={"model": "microsoft/Phi-3.5-mini-instruct"},
generation_kwargs={"max_tokens": 20},
)
@ -598,7 +598,7 @@ class TestHuggingFaceAPIChatGenerator:
def test_live_run_serverless_streaming(self):
generator = HuggingFaceAPIChatGenerator(
api_type=HFGenerationAPIType.SERVERLESS_INFERENCE_API,
api_params={"model": "mistralai/Mistral-7B-Instruct-v0.3"},
api_params={"model": "microsoft/Phi-3.5-mini-instruct"},
generation_kwargs={"max_tokens": 20},
streaming_callback=streaming_callback_handler,
)
@ -825,7 +825,7 @@ class TestHuggingFaceAPIChatGenerator:
async def test_live_run_async_serverless(self):
generator = HuggingFaceAPIChatGenerator(
api_type=HFGenerationAPIType.SERVERLESS_INFERENCE_API,
api_params={"model": "mistralai/Mistral-7B-Instruct-v0.3"},
api_params={"model": "microsoft/Phi-3.5-mini-instruct"},
generation_kwargs={"max_tokens": 20},
)

10
test/components/generators/test_hugging_face_api.py
View File

@ -298,14 +298,14 @@ class TestHuggingFaceAPIGenerator:
def test_run_serverless(self):
generator = HuggingFaceAPIGenerator(
api_type=HFGenerationAPIType.SERVERLESS_INFERENCE_API,
api_params={"model": "mistralai/Mistral-7B-Instruct-v0.3"},
api_params={"model": "microsoft/Phi-3.5-mini-instruct"},
generation_kwargs={"max_new_tokens": 20},
)
# You must include the instruction tokens in the prompt. HF does not add them automatically.
# Without them the model will behave erratically.
response = generator.run(
"<s>[INST] What is the capital of France? Be concise only provide the capital, nothing else.[/INST]"
"<|user|>\nWhat is the capital of France? Be concise only provide the capital, nothing else.<|end|>\n<|assistant|>\n"
)
# Assert that the response contains the generated replies
@ -329,12 +329,14 @@ class TestHuggingFaceAPIGenerator:
def test_live_run_streaming_check_completion_start_time(self):
generator = HuggingFaceAPIGenerator(
api_type=HFGenerationAPIType.SERVERLESS_INFERENCE_API,
api_params={"model": "HuggingFaceH4/zephyr-7b-beta"},
api_params={"model": "microsoft/Phi-3.5-mini-instruct"},
generation_kwargs={"max_new_tokens": 30},
streaming_callback=streaming_callback_handler,
)
results = generator.run("You are a helpful agent that answers questions. What is the capital of France?")
results = generator.run(
"<|user|>\nWhat is the capital of France? Be concise only provide the capital, nothing else.<|end|>\n<|assistant|>\n"
)
# Assert that the response contains the generated replies
assert "replies" in results