Update app.py

app.py

@@ -4,13 +4,12 @@ from transformers import pipeline
 # Function to get response from LLaMA 2 model
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+
 
 def getLLamaresponse(input_text, keywords, blog_style):
     # Load the LLaMA 2 model from Hugging Face
-    #model_name = model
-    #llm = pipeline('text-generation', model=model_name)
+    model_name = "https://api-inference.huggingface.co/models/mistralai/mathstral-7B-v0.1"
+    llm = pipeline('text-generation', model=model_name)
 
     # Prompt Template
     template = """
@@ -21,7 +20,7 @@ def getLLamaresponse(input_text, keywords, blog_style):
     prompt = template.format(blog_style=blog_style, input_text=input_text, keywords=keywords)
 
     # Generate the response from the LLaMA 2 model
-    response = model(prompt, max_length=250, temperature=0.01)
+    response = llm(prompt, max_length=250, temperature=0.01)
     return response[0]['generated_text']
 
 st.set_page_config(page_title="Generate Project Idea",