Update app.py

app.py

@@ -8,7 +8,7 @@ from huggingface_hub import hf_hub_download #load from huggingfaces
 
 llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/Vigogne-2-7B-Instruct-GGML", filename="vigogne-2-7b-instruct.ggmlv3.q4_1.bin"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
 
-description = " Bro i dont want learn! i just want results "
+description = " Bro i dont want learn! i just want results(https://github.com/abetlen/llama-cpp-python)"
 def generate_text(input_text):
     output = llm(f"Q: {input_text} \n A:", max_tokens=521, stop=["Q:", "\n"], echo=True,)
     return output['choices'][0]['text']
@@ -17,6 +17,6 @@ def generate_text(input_text):
 input_text = gr.inputs.Textbox(lines= 10, label="Enter your input text")
 output_text = gr.outputs.Textbox(label="Output text")
 
-demo = gr.Interface(fn=generate_text, inputs=input_text, outputs=output_text, title="Running Llama on CPU is Hard", description=description, examples=examples)
+demo = gr.Interface(fn=generate_text, inputs=input_text, outputs=output_text, title="Running Llama on CPU is Hard", description=description)
 demo.queue()
 demo.launch()