From 27bc1271d14f85041a4e493d2e59cd06a4fc4a06 Mon Sep 17 00:00:00 2001 From: drbh Date: Thu, 6 Nov 2025 19:42:45 +0000 Subject: [PATCH] fix: prefer meta-llama/Llama-2-7b-hf over deprecated repo --- integration-tests/models/test_flash_llama.py | 2 +- server/tests/models/test_model.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/integration-tests/models/test_flash_llama.py b/integration-tests/models/test_flash_llama.py index bf49dc0b..1db58449 100644 --- a/integration-tests/models/test_flash_llama.py +++ b/integration-tests/models/test_flash_llama.py @@ -3,7 +3,7 @@ import pytest @pytest.fixture(scope="module") def flash_llama_handle(launcher): - with launcher("huggingface/llama-7b", num_shard=2) as handle: + with launcher("meta-llama/Llama-2-7b-hf", num_shard=2) as handle: yield handle diff --git a/server/tests/models/test_model.py b/server/tests/models/test_model.py index 8441e8c6..46a27253 100644 --- a/server/tests/models/test_model.py +++ b/server/tests/models/test_model.py @@ -14,7 +14,7 @@ def get_test_model(): def generate_token(self, batch): raise NotImplementedError - tokenizer = AutoTokenizer.from_pretrained("huggingface/llama-7b") + tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf") model = TestModel( "test_model_id",