Update app.py

app.py

@@ -310,12 +310,14 @@ demo = gr.Interface(
     title="FinGPT-Forecaster",
     description="""FinGPT-Forecaster takes random market news and optional basic financials related to the specified company from the past few weeks as input and responds with the company's **positive developments** and **potential concerns**. Then it gives out a **prediction** of stock price movement for the coming week and its **analysis** summary.
 
-This model is finetuned on Llama2-7b-chat-hf with LoRA on the past year's DOW30 market data. Inference in this demo uses fp16 and **welcomes any ticker symbol**.
+This model is finetuned on Llama2-7b-chat-hf with LoRA on the past year's DOW30 market data but **welcomes any ticker symbol**.
 Company profile & Market news & Basic financials & Stock prices are retrieved using **yfinance & finnhub**.
 For more detailed and customized implementation, refer to our FinGPT project: <https://github.com/AI4Finance-Foundation/FinGPT>
 
-⚠️Warning: This is just a demo showing what this model is capable of. During each individual inference, company news is **randomly sampled** from all the news from designated weeks, which might result in **different predictions for the same time period**.
-We suggest users deploy the [original model](https://huggingface.co/FinGPT/fingpt-forecaster_dow30_llama2-7b_lora) or clone this space and inference with more carefully selected news in their own favorable ways.
+This demo has been downgraded to using **T4 with 8-bit inference** due to cost considerations, speed & performance may be affected.
+
+⚠️Warning: This is just a demo showing what this model can do. During each individual inference, company news is **randomly sampled** from all the news from designated weeks, which might result in **different predictions for the same period**. 
+We suggest users deploy the [original model](https://huggingface.co/FinGPT/fingpt-forecaster_dow30_llama2-7b_lora) or clone this space and inference with more carefully selected news in their favorable ways.
 Setting do_sample=False or modifying the temperature during the generation process also helps stabilize the prediction result. 
 
 **Disclaimer: Nothing herein is financial advice, and NOT a recommendation to trade real money. Please use common sense and always first consult a professional before trading or investing.**