Update app.py

app.py

@@ -81,11 +81,21 @@ def get_chain(temperature):
     
     # Replace the local OLMOLLM with the Hugging Face model
     
-    model_name = "gpt2"
-    pipe = pipeline("text-generation", model=model_name,
-                    max_length=2500,  # Allows for 2,093 input tokens + some generated tokens
-                    max_new_tokens=200,
-                    temperature = temperature)
+    model_name = "OLMo-7B-Instruct-Q4_K_M"
+
+# Load the tokenizer and model
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+
+    # Create a text generation pipeline with the model
+    pipe = pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+        max_length=2200,  # Adjust based on your input length
+        max_new_tokens=100,  # Number of tokens to generate
+        temperature=temperature  # Adjust the creativity of the output
+                )
 
     
     # Initialize the LangChain HuggingFacePipeline