Update app.py

app.py

@@ -5,22 +5,23 @@ from huggingface_hub import hf_hub_download
 title = "Mistral-7B-Instruct-GGUF Run On CPU-Basic Free Hardware"
 
 description = """
-🔎 [Mistral AI's Mistral 7B Instruct v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) [GGUF format model](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF) , 4-bit quantization balanced quality gguf version, running on CPU. English Only (Also support other languages but the quality's not good). Using [GitHub - llama.cpp](https://github.com/ggerganov/llama.cpp) [GitHub - gpt4all](https://github.com/nomic-ai/gpt4all). 
+🔎 [Mistral AI's Mistral 7B Instruct v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) [GGUF format model](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF), 4-bit quantization balanced quality GGUF version, running on CPU. English Only (supports other languages but with reduced quality). Using [GitHub - llama.cpp](https://github.com/ggerganov/llama.cpp) and [GitHub - gpt4all](https://github.com/nomic-ai/gpt4all). 
 🔨 Running on CPU-Basic free hardware. Suggest duplicating this space to run without a queue. 
-Mistral does not support system prompt symbol (such as ```<<SYS>>```) now, input your system prompt in the first message if you need. Learn more: [Guardrailing Mistral 7B](https://docs.mistral.ai/usage/guardrailing). 
-"""
-
-"""
-[Model From TheBloke/Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF)
-[Mistral-instruct-v0.1 System prompt](https://docs.mistral.ai/usage/guardrailing)
+Mistral does not support system prompt symbols (such as `<<SYS>>`) now, input your system prompt in the first message if needed. Learn more: [Guardrailing Mistral 7B](https://docs.mistral.ai/usage/guardrailing). 
 """
 
 model_path = "models"
 model_name = "unsloth.Q4_K_M.gguf"
-hf_hub_download(repo_id="vislupus/bulgarian-joke-master-gemma-2-2b-it-bnb-4bit-gguf", filename=model_name, local_dir=model_path, local_dir_use_symlinks=False)
+
+# Download the model from Hugging Face
+hf_hub_download(
+    repo_id="vislupus/bulgarian-joke-master-gemma-2-2b-it-bnb-4bit-gguf",
+    filename=model_name,
+    local_dir=model_path
+)
 
 print("Start the model init process")
-model = model = GPT4All(model_name, model_path, allow_download = False, device="cpu")
+model = GPT4All(model_name, model_path)
 print("Finish the model init process")
 
 model.config["promptTemplate"] = "[INST] {0} [/INST]"
@@ -36,7 +37,7 @@ def generater(message, history, temperature, top_p, top_k):
         prompt += assistant_message + "</s>"
     prompt += model.config["promptTemplate"].format(message)
     outputs = []    
-    for token in model.generate(prompt=prompt, temp=temperature, top_k = top_k, top_p = top_p, max_tokens = max_new_tokens, streaming=True):
+    for token in model.generate(prompt=prompt, temp=temperature, top_k=top_k, top_p=top_p, max_tokens=max_new_tokens, streaming=True):
         outputs.append(token)
         yield "".join(outputs)
 
@@ -46,9 +47,9 @@ def vote(data: gr.LikeData):
     else:
         return
 
-chatbot = gr.Chatbot(avatar_images=('resourse/user-icon.png', 'resourse/chatbot-icon.png'),bubble_full_width = False)
+chatbot = gr.Chatbot(avatar_images=('resourse/user-icon.png', 'resourse/chatbot-icon.png'), bubble_full_width=False)
 
-additional_inputs=[
+additional_inputs = [
     gr.Slider(
         label="temperature",
         value=0.5,
@@ -65,7 +66,7 @@ additional_inputs=[
         maximum=1.0,
         step=0.01,
         interactive=True,
-        info="0.1 means only the tokens comprising the top 10% probability mass are considered. Suggest set to 1 and use temperature. 1 means 100% and will disable it",
+        info="0.1 means only the tokens comprising the top 10% probability mass are considered. Suggest set to 1 and use temperature. 1 means 100% and will disable it.",
     ),
     gr.Slider(
         label="top_k",
@@ -74,7 +75,7 @@ additional_inputs=[
         maximum=1000,
         step=1,
         interactive=True,
-        info="limits candidate tokens to a fixed number after sorting by probability. Setting it higher than the vocabulary size deactivates this limit.",
+        info="Limits candidate tokens to a fixed number after sorting by probability. Setting it higher than the vocabulary size deactivates this limit.",
     )
 ]
 
@@ -82,9 +83,9 @@ character = "Sherlock Holmes"
 series = "Arthur Conan Doyle's novel"
 
 iface = gr.ChatInterface(
-    fn = generater,
+    fn=generater,
     title=title,
-    description = description,
+    description=description,
     chatbot=chatbot,
     additional_inputs=additional_inputs,
     examples=[
@@ -101,4 +102,4 @@ with gr.Blocks(css="resourse/style/custom.css") as demo:
     iface.render()
 
 if __name__ == "__main__":
-    demo.queue(max_size=3).launch()
+    demo.queue(max_size=3).launch()