Update demo.py

demo.py

@@ -178,15 +178,9 @@ def get_demo():
                 gr.Markdown(
                     """**Chat with [Falcon-7B-Instruct](https://huggingface.co/tiiuae/falcon-7b-instruct), brainstorm ideas, discuss your holiday plans, and more!**
 
-                    ✨ This demo is powered by [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b), finetuned on the [Baize](https://github.com/project-baize/baize-chatbot) dataset, and running with [Text Generation Inference](https://github.com/huggingface/text-generation-inference). [Falcon-7B](https://huggingface.co/tiiuae/falcon-40b) is a state-of-the-art large language model built by the [Technology Innovation Institute](https://www.tii.ae) in Abu Dhabi. It is trained on 1 trillion tokens (including [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)) and available under the Apache 2.0 license. It currently holds the 🥇 1st place on the [🤗 Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). This demo is made available by the [HuggingFace H4 team](https://huggingface.co/HuggingFaceH4). 
+                    ✨ This demo is powered by [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b), finetuned on the [Baize](https://github.com/project-baize/baize-chatbot) dataset, and running with [Text Generation Inference](https://github.com/huggingface/text-generation-inference). 
 
-                    🧪 This is only a **first experimental preview**: the [H4 team](https://huggingface.co/HuggingFaceH4) intends to provide increasingly capable versions of Falcon Chat in the future, based on improved datasets and RLHF/RLAIF.
-
-                    👀 **Learn more about Falcon LLM:** [falconllm.tii.ae](https://falconllm.tii.ae/)
-
-                    ➡️️ **Intended Use**: this demo is intended to showcase an early finetuning of [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b), to illustrate the impact (and limitations) of finetuning on a dataset of conversations and instructions. We encourage the community to further build upon the base model, and to create even better instruct/chat versions!
-
-                    ⚠️ **Limitations**: the model can and will produce factually incorrect information, hallucinating facts and actions. As it has not undergone any advanced tuning/alignment, it can produce problematic outputs, especially if prompted to do so. Finally, this demo is limited to a session length of about 1,000 words.
+                    🧪 This uses a quantized [ggml](https://github.com/ggerganov/ggml) optimized for CPU. Special thanks to [ggllm.cpp](https://github.com/cmp-nct/ggllm.cpp), [ctransformers](https://github.com/marella/ctransformers), and [TheBloke](https://huggingface.co/TheBloke).
                     """
                 )