MrOvkill
/

gemma-2-inference-endpoint-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

MrOvkill commited on Mar 6, 2024

Commit

9afbac2

·

1 Parent(s): 96aa541

NOW 0.1!

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -4,7 +4,7 @@ from llama_cpp import Llama
 MAX_TOKENS=8192
 class EndpointHandler():
-    def __init__(self):
         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]]:

 MAX_TOKENS=8192
 class EndpointHandler():
+    def __init__(self, data):
         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]]: