update app.py

app.py

@@ -57,12 +57,12 @@ def summarize_text(title,text):
     from transformers import BitsAndBytesConfig
     from transformers import AutoTokenizer, AutoModelForCausalLM
 
-    quantization_config = BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_compute_dtype=torch.float16,
-        bnb_4bit_quant_type="nf4",
-        bnb_4bit_use_double_quant=True,
-    )
+    # quantization_config = BitsAndBytesConfig(
+    #     load_in_4bit=True,
+    #     bnb_4bit_compute_dtype=torch.float16,
+    #     bnb_4bit_quant_type="nf4",
+    #     bnb_4bit_use_double_quant=True,
+    # )
 
     # model = "nomic-ai/gpt4all-falcon"
     model = "tiiuae/falcon-7b-instruct"
@@ -70,7 +70,7 @@ def summarize_text(title,text):
     tokenizer = AutoTokenizer.from_pretrained(model,trust_remote_code=True,)
     model = AutoModelForCausalLM.from_pretrained(model,
                                                 # trust_remote_code=True,
-                                                quantization_config=quantization_config,
+                                                # quantization_config=quantization_config,
                                                 )
 
     from langchain import HuggingFacePipeline