taylorj94
/

Llama-3.2-1B

Text Generation

text-generation-inference

Model card Files Files and versions

taylorj94 commited on Dec 27, 2024

Commit

c0e19b5

·

verified ·

1 Parent(s): d83ea90

Update handler.py

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -11,7 +11,7 @@ class EndpointHandler:
         """
         self.model = Llama.from_pretrained(
             repo_id="bartowski/Meta-Llama-3.1-8B-Instruct-GGUF",
-            filename="Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
         )
         self.tokenizer = AutoTokenizer.from_pretrained("taylorj94/Llama-3.2-1B")

         """
         self.model = Llama.from_pretrained(
             repo_id="bartowski/Meta-Llama-3.1-8B-Instruct-GGUF",
+            filename="Meta-Llama-3.1-8B-Instruct-Q6_K.gguf"
         )
         self.tokenizer = AutoTokenizer.from_pretrained("taylorj94/Llama-3.2-1B")