MrOvkill
/

gemma-2-inference-endpoint-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

MrOvkill commited on Mar 6, 2024

Commit

df7ea15

·

1 Parent(s): d3a7ccf

Fix handler Attempt 2

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -3,7 +3,7 @@ from llama_cpp import Llama
 class EndpointHandler():
     def __init__(self, path="", vision_model="obsidian3b"):
-        self.model = Llama("MrOvkill/gemma-2-inference-endpoint-GGUF", filename="gemma-2b.q8_0.gguf")
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
         """

 class EndpointHandler():
     def __init__(self, path="", vision_model="obsidian3b"):
+        self.model = Llama.from_pretrained("MrOvkill/gemma-2-inference-endpoint-GGUF", filename="gemma-2b.q8_0.gguf")
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
         """