fix: prefer meta-llama/Llama-2-7b-hf over deprecated repo

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
 
 

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",