Update app.py

app.py

@@ -6,35 +6,7 @@ import psutil
 from ctransformers import AutoModelForCausalLM
 from huggingface_hub import hf_hub_download
 
-_ = """
-snapshot_download(
-  repo_id="TheBloke/Luna-AI-Llama2-Uncensored-GGML",
-  allow_patterns="luna-ai-llama2-uncensored.ggmlv3.q2_K.bin",
-  revision="main",
-  local_dir="models",
-  local_dir_use_symlinks=False,  # default "auto"
-)
-
-hf_hub_download(
-    repo_id=repo_id,
-    filename=model_filename,
-    local_dir=local_path,
-    local_dir_use_symlinks=True,
-)
-# """
-# 4.06G
-
-_ = """
-llm = AutoModelForCausalLM.from_pretrained(
-    "TheBloke/Luna-AI-Llama2-Uncensored-GGML",
-    model_file="luna-ai-llama2-uncensored.ggmlv3.q2_K.bin",
-    model_type="llama", gpu_layers=32, threads=2,
-)
-# """
-# _ = Path("models", "luna-ai-llama2-uncensored.ggmlv3.q2_K.bin").absolute().as_posix()
-# assert Path(_).exists(), f"{_} does not exist, perhaps snapshot_download failed?"
 
-# URL = "https://huggingface.co/TheBloke/falcon-7b-instruct-GGML/blob/main/falcon-7b-instruct.ggccv1.q4_1.bin"
 URL = "https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGML/resolve/main/luna-ai-llama2-uncensored.ggmlv3.q2_K.bin"
 repo_id = "/".join(urlparse(URL).path.strip("/").split("/")[:2])
 
@@ -50,9 +22,6 @@ _ = hf_hub_download(
 )
 
 llm = AutoModelForCausalLM.from_pretrained(
-    # repo_id,  # "TheBloke/falcon-7b-instruct-GGML",
-    # model_file=model_file,
-    # model_file=_,
     _,
     model_type="llama",
     threads=psutil.cpu_count(logical=False),
@@ -112,7 +81,7 @@ def chat():
 
     with gr.Row(elem_id="button_container"):
         with gr.Column():
-            retry_button = gr.Button("♻️ Retry last turn")
+            retry_button = gr.Button("♻️ Retry")
         with gr.Column():
             delete_turn_button = gr.Button("🧽 Delete last turn")
         with gr.Column():
@@ -120,15 +89,12 @@ def chat():
 
     gr.Examples(
         [
-            ["Hey Falcon! Any recommendations for my holidays in Abu Dhabi?"],
+            ["Hey! Any recommendations for my holidays"],
             ["What's the Everett interpretation of quantum mechanics?"],
             [
                 "Give me a list of the top 10 dive sites you would recommend around the world."
             ],
             ["Can you tell me more about deep-water soloing?"],
-            [
-                "Can you write a short tweet about the Apache 2.0 release of our latest AI model, Falcon LLM?"
-            ],
         ],
         inputs=inputs,
         label="Click on any example and press Enter in the input textbox!",
@@ -237,17 +203,7 @@ def get_demo():
         with gr.Row():
             with gr.Column():
                 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-7b) 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 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.
+                    """**Chat with [TheBloke/Luna-AI-Llama2-Uncensored-GGML](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGML), brainstorm ideas, discuss your holiday plans, and more!**
                     """
                 )