Update app.py

app.py

@@ -5,17 +5,12 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 import torch
 import os
 
-title = """
-# Welcome to 🌟Tonic's🫡Command-R
-🫡Command-R is a Large Language Model optimized for conversational interaction and long context tasks. It targets the “scalable” category of models that balance high performance with strong accuracy, enabling companies to move beyond proof of concept, and into production. 🫡Command-R boasts high precision on retrieval augmented generation (RAG) and tool use tasks, low latency and high throughput, a long 128k context, and strong capabilities across 10 key languages. You can build with this endpoint using🫡Command-R available here : [CohereForAI/c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01). You can also use 🫡Command-R by cloning this space. Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/Command-R?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3> 
-Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/GWpVpekp) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) Math 🔍 [introspector](https://huggingface.co/introspector) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [Torchon](https://github.com/Tonic-AI/Torchon)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗
-"""
 
-bnb_config = AwqConfig(group_size=512)
+bnb_config = BitsAndBytesConfig(load_in_8bit=True)
 
 model_id = "CohereForAI/c4ai-command-r-v01"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config,pre_quantized=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)
 
 @spaces.GPU
 def generate_response(user_input, max_new_tokens, temperature):
@@ -52,7 +47,6 @@ def load_example(choice):
 
 
 with gr.Blocks() as demo:
-    gr.Markdown(title)
     with gr.Row():
         max_new_tokens_slider = gr.Slider(minimum=100, maximum=4000, value=980, label="Max New Tokens")
         temperature_slider = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, value=0.3, label="Temperature")