Update app.py

app.py

@@ -19,20 +19,12 @@ import requests
 client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
 MODEL = 'llama3-groq-70b-8192-tool-use-preview'
 
-# Configure BitsAndBytes for 4-bit quantization
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
-
 ############### MINICPM MEIN ERROR HAI, USKO REPLACE KARNA HOGA ###############
 
 # Load MiniCPM-V-2_6 with 4-bit quantization
-text_model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True,
-                                      quantization_config=bnb_config, device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True)
+text_model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2', trust_remote_code=True,
+                                       device_map="auto", dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2', trust_remote_code=True)
 
 tts_model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-large-v1").to('cuda')
 tts_tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-large-v1")