lab2 test

app.py

@@ -1,12 +1,10 @@
 import gradio as gr
 
-from llama_cpp import Llama
-
-llm = Llama.from_pretrained(
-    repo_id="ID2223JR/gguf_model",
-    filename="GGUF_FILE",
-)
+# Load model directly
+from transformers import AutoModel, AutoTokenizer
 
+model = AutoModel.from_pretrained("ID2223JR/gguf_model")
+tokenizer = AutoTokenizer.from_pretrained("ID2223JR/gguf_model")
 
 # Data storage
 ingredients_list = []
@@ -40,8 +38,13 @@ def submit_to_model():
         ingredients_list
     )
 
-    response = llm.create_chat_completion(messages=prompt)
-    return response.choices[0].text
+    # Tokenize and pass the prompt to the model
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=100)
+
+    # Decode the model output
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
 
 # App

requirements.txt

@@ -1,2 +1,3 @@
 gradio==5.1.0
-llama-cpp-python==0.2.24
+llama-cpp-python==0.2.24
+transformers==4.46.3