DeepInfra
/

Llama-2-70b-chat-hf-trt-fp8

Model card Files Files and versions Community

yessenzhar commited on Dec 8, 2023

Commit

d5c7a29

•

1 Parent(s): 0e96839

remove print

Files changed (1) hide show

postprocessing/1/model.py +0 -1

postprocessing/1/model.py CHANGED Viewed

@@ -181,7 +181,6 @@ class TritonPythonModel:
                     output = self._single_token_decode(tokens[0])
                 else:
                     output = self.tokenizer.decode(tokens)
-                print(output)
                 outputs.append(output.encode('utf8'))
                 total_len += len(tokens)
             output_lens.append(total_len)

                     output = self._single_token_decode(tokens[0])
                 else:
                     output = self.tokenizer.decode(tokens)
                 outputs.append(output.encode('utf8'))
                 total_len += len(tokens)
             output_lens.append(total_len)