Update app.py

app.py

@@ -56,17 +56,23 @@ model_id = "TheBloke/zephyr-7B-beta-GGUF"
 device = "cpu"
 
 
-llm_model = CTransformers(
-    model="TheBloke/zephyr-7B-beta-GGUF",
-    model_type="mistral",
-    max_new_tokens=4384,
-    temperature=0.2,
-    repetition_penalty=1.13,
-    device=device  # Set the device explicitly during model initialization
-)
+# llm_model = CTransformers(
+#     model="TheBloke/zephyr-7B-beta-GGUF",
+#     model_type="mistral",
+#     max_new_tokens=4384,
+#     temperature=0.2,
+#     repetition_penalty=1.13,
+#     device=device  # Set the device explicitly during model initialization
+# )
+
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
+tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
+model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# tokenizer = AutoTokenizer.from_pretrained(model_id)
 # model = AutoModelForCausalLM.from_pretrained(model_id)
 
 # pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=10)