hf_text-generation-inference/integration-tests/models/test_mt0_base.py

65 lines
1.6 KiB
Python
Raw Permalink Normal View History

2023-05-15 15:36:30 -06:00
import pytest
@pytest.fixture(scope="module")
def mt0_base_handle(launcher):
with launcher("bigscience/mt0-base") as handle:
yield handle
2023-05-15 15:36:30 -06:00
@pytest.fixture(scope="module")
async def mt0_base(mt0_base_handle):
2023-05-31 02:55:59 -06:00
await mt0_base_handle.health(300)
return mt0_base_handle.client
2023-05-15 15:36:30 -06:00
@pytest.mark.asyncio
async def test_mt0_base(mt0_base, response_snapshot):
2023-05-15 15:36:30 -06:00
response = await mt0_base.generate(
"Why is the sky blue?",
max_new_tokens=10,
top_p=0.9,
decoder_input_details=True,
2023-05-15 15:36:30 -06:00
seed=0,
)
assert response.details.generated_tokens == 5
assert response == response_snapshot
2023-05-15 15:36:30 -06:00
@pytest.mark.asyncio
async def test_mt0_base_all_params(mt0_base, response_snapshot):
2023-05-15 15:36:30 -06:00
response = await mt0_base.generate(
"Why is the sky blue?",
max_new_tokens=10,
repetition_penalty=1.2,
return_full_text=True,
stop_sequences=["test"],
temperature=0.5,
top_p=0.9,
top_k=10,
truncate=5,
typical_p=0.9,
watermark=True,
decoder_input_details=True,
2023-05-15 15:36:30 -06:00
seed=0,
)
Adding Llava-Next (Llava 1.6) with full support. (#1709) # What does this PR do? - Changed all models to extract `embed_tokens` in order to enable llava to separately call the embeddings and the core model layers. - Added VlmCausalLM to inherit from FlashMistral in order to be maximally supported. The only added logics sits on top and parses images into pixel values, preallocates input_ids space for the image embeddings, and passes them for the model. - Added Clip for the vision tower. - Didn't add flash for the vision tower since there's no padding anyway. - Added heuristic (potentially incomplete) to calculate number of features *before* calculating the clip patches (allows for easier logic reuse of the LLM under the hood). Still needs to be done: - [x] Implement the image parsing in the controller side, to avoid downloading n times per TP shard and also refusing requests too large early and avoid issues where the truncation actually truncates the image. - [ ] Make sure it works with quantization properly. - [x] Make sure it works with TP>1 <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
2024-04-09 13:32:00 -06:00
assert response.details.generated_tokens == 10
assert response == response_snapshot
2023-05-15 15:36:30 -06:00
@pytest.mark.asyncio
async def test_mt0_base_load(mt0_base, generate_load, response_snapshot):
2023-05-15 15:36:30 -06:00
responses = await generate_load(
mt0_base,
"Why is the sky blue?",
max_new_tokens=10,
n=4,
)
assert len(responses) == 4
assert all([r.generated_text == responses[0].generated_text for r in responses])
2023-05-15 15:36:30 -06:00
assert responses == response_snapshot