lewtun
/

chip-12B-instruct-alpha

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

lewtun HF staff commited on Feb 1, 2023

Commit

685099d

·

1 Parent(s): 70740f7

Update handler.py

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -5,7 +5,7 @@ import torch
 class EndpointHandler:
     def __init__(self, path=""):
         # load model and processor from path
-        self.model =  AutoModelForCasualLM.from_pretrained(path, device_map="auto", load_in_8bit=True)
         self.tokenizer = AutoTokenizer.from_pretrained(path)
     def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:

 class EndpointHandler:
     def __init__(self, path=""):
         # load model and processor from path
+        self.model =  AutoModelForCausalLM.from_pretrained(path, device_map="auto", load_in_8bit=True)
         self.tokenizer = AutoTokenizer.from_pretrained(path)
     def __call__(self, data: Dict[str, Any]) -> Dict[str, str]: