i

app.py

@@ -23,7 +23,7 @@ def get_completion(prompt, model="dolly-v0-70m"):
         model=model,
         messages=messages,
         temperature=0, # this is the degree of randomness of the model's output
-    )
+	)
 
 	# Examples from https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html
 	instructions = [prompt]
@@ -31,9 +31,9 @@ def get_completion(prompt, model="dolly-v0-70m"):
 	# set some additional pipeline args
 	pipeline_kwargs = {'torch_dtype': "auto"}
 	#if gpu_family == "v100":
-    #pipeline_kwargs['torch_dtype'] = "float16"
+	#pipeline_kwargs['torch_dtype'] = "float16"
 	#elif gpu_family == "a10" or gpu_family == "a100":
-    #pipeline_kwargs['torch_dtype'] = "bfloat16"
+	#pipeline_kwargs['torch_dtype'] = "bfloat16"
 
 	pipeline_kwargs['max_new_tokens'] = 300