huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Working integration-tests.

Browse Source
This commit is contained in:
Nicolas Patry 2024-05-15 10:17:07 +00:00
parent 17ac93efd3
commit 65bc0aaa58
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
integration-tests/models/__snapshots__/test_flash_pali_gemma/test_flash_pali_gemma.json
View File

@ -8,13 +8,13 @@
"tokens": [ "tokens": [
{ {
"id": 54901, "id": 54901,
"logprob": -0.61621094, "logprob": -0.72753906,
"special": false, "special": false,
"text": "beach" "text": "beach"
}, },
{ {
"id": 1, "id": 1,
"logprob": -0.11273193, "logprob": -0.011009216,
"special": true, "special": true,
"text": "<eos>" "text": "<eos>"
} }

3
integration-tests/models/test_flash_pali_gemma.py
View File

@ -7,8 +7,9 @@ import base64
@pytest.fixture(scope="module") @pytest.fixture(scope="module")
def flash_pali_gemma_handle(launcher): def flash_pali_gemma_handle(launcher):
with launcher( with launcher(
"gv-hf/paligemma-3b-mix-224", "google/paligemma-3b-pt-224",
num_shard=1, num_shard=1,
revision="float16",
max_input_length=4000, max_input_length=4000,
max_total_tokens=4096, max_total_tokens=4096,
) as handle: ) as handle: