llama-server: update test models to new HF repos

Author: ServeurpersoCom

tools/server/tests/unit/test_router.py

@@ -104,8 +104,8 @@ def test_router_models_max_evicts_lru():
 
     candidate_models = [
         "ggml-org/tinygemma3-GGUF:Q8_0",
-        "ggml-org/models/tinyllamas/stories260K.gguf",
-        "ggml-org/models/bert-bge-small/ggml-model-f16.gguf",
+        "ggml-org/test-model-stories260K",
+        "ggml-org/test-model-stories260K-infill",
     ]
 
     loaded_models: list[str] = []

tools/server/tests/utils.py

@@ -450,8 +450,8 @@ def load_all() -> None:
     @staticmethod
     def tinyllama2() -> ServerProcess:
         server = ServerProcess()
-        server.model_hf_repo = "ggml-org/models"
-        server.model_hf_file = "tinyllamas/stories260K.gguf"
+        server.model_hf_repo = "ggml-org/test-model-stories260K"
+        server.model_hf_file = None
         server.model_alias = "tinyllama-2"
         server.n_ctx = 512
         server.n_batch = 32
@@ -495,8 +495,8 @@ def bert_bge_small_with_fa() -> ServerProcess:
     def tinyllama_infill() -> ServerProcess:
         server = ServerProcess()
         server.offline = True # will be downloaded by load_all()
-        server.model_hf_repo = "ggml-org/models"
-        server.model_hf_file = "tinyllamas/stories260K-infill.gguf"
+        server.model_hf_repo = "ggml-org/test-model-stories260K-infill"
+        server.model_hf_file = None
         server.model_alias = "tinyllama-infill"
         server.n_ctx = 2048
         server.n_batch = 1024