import spaces
import gradio as gr
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch

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✨StarCoder available here : [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b). 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 = 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)

@spaces.GPU
def generate_response(user_input, max_new_tokens, temperature):
    messages = [{"role": "user", "content": user_input}]
    input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")

    # Generate tokens
    gen_tokens = model.generate(
        input_ids['input_ids'], 
        max_length=max_new_tokens + input_ids['input_ids'].shape[1],  # Adjusting max_length to account for input length
        do_sample=True, 
        temperature=temperature,
    )

    # Decode tokens to string
    gen_text = tokenizer.decode(gen_tokens[0])
    return gen_text


examples = [
        {"message": "What is the weather like today?", "max_new_tokens": 250, "temperature": 0.5},
        {"message": "Tell me a joke.", "max_new_tokens": 650, "temperature": 0.7},
        {"message": "Explain the concept of machine learning.", "max_new_tokens": 980, "temperature": 0.4}
]

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")
    message_box = gr.Textbox(lines=2, label="Your Message")
    generate_button = gr.Button("Try🫡Command-R")
    output_box = gr.Textbox(label="🫡Command-R")
    with gr.Accordion("🫡Examples", open=True):
        gr.Examples(
            examples=examples,
            inputs=[message_box, max_new_tokens_slider, temperature_slider],
            outputs=output_box,
            fn=generate_response,
            cache_examples=True
        )

    generate_button.click(
        fn=generate_response,
        inputs=[message_box, max_new_tokens_slider, temperature_slider],
        outputs=output_box
    )
demo.launch()