app.py

import gradio as gr
import spaces
from huggingface_hub import InferenceClient
import os
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
# pip install 'git+https://github.com/huggingface/transformers.git'

from transformers import AutoTokenizer, AutoModelForCausalLM

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

bnb_config = BitsAndBytesConfig(load_in_8bit=True)

token=os.getenv('token')
print('token = ',token)
model_id = "CohereForAI/c4ai-command-r-plus"
tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
model = AutoModelForCausalLM.from_pretrained(model_id, token= token, quantization_config=bnb_config)

# Format message with the command-r-plus chat template
messages = [{"role": "user", "content": "Hello, how are you?"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>

gen_tokens = model.generate(
    input_ids, 
    max_new_tokens=100, 
    do_sample=True, 
    temperature=0.3,
    )

gen_text = tokenizer.decode(gen_tokens[0])
print(gen_text)


@spaces.GPU(duration=120)
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    messages = [{"role": "user", "content": "Hello, how are you?"}]
    input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
    ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
    
    gen_tokens = model.generate(
        input_ids, 
        max_new_tokens=100, 
        do_sample=True, 
        temperature=0.3,
        )
    
    gen_text = tokenizer.decode(gen_tokens[0])
    print(gen_text)
    yield gen_text
    # for val in history:
    #     if val[0]:
    #         messages.append({"role": "user", "content": val[0]})
    #     if val[1]:
    #         messages.append({"role": "assistant", "content": val[1]})

    # messages.append({"role": "user", "content": message})

    # response = ""

    # for message in client.chat_completion(
    #     messages,
    #     max_tokens=max_tokens,
    #     stream=True,
    #     temperature=temperature,
    #     top_p=top_p,
    # ):
    #     token = message.choices[0].delta.content

    #     response += token
    #     yield response

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()