12

app.py

@@ -19,7 +19,7 @@ schemes_info_coll = db["schemes_embedded"]
 query_logs_coll = db["query_logs"]
 
 # === LLM ===
-model_id = "Vipplav/gemma-finetuned-faq"
+model_id = "google/gemma-2b-it"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32)
 generator = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=128, do_sample=False)