app.py

import gradio as gr
import spaces
import torch

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'



token=os.getenv('token')
print('token = ',token)

from transformers import AutoModelForCausalLM, AutoTokenizer

# model_id = "mistralai/Mistral-7B-v0.3"

# model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"

from airllm import AirLLMLlama2

MAX_LENGTH = 128


hf_hub_download(
    repo_id="CohereForAI/c4ai-command-r-plus-4bit",
    # filename="Meta-Llama-3-70B-Instruct-Q3_K_M.gguf",
    local_dir = "./models",
    token= token
)

# could use hugging face model repo id:
model = AirLLMLlama2("./models", )


# tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)

# model = AutoModelForCausalLM.from_pretrained(model_id, token= token, torch_dtype=torch.bfloat16,    
#                                              # attn_implementation="flash_attention_2",
#                                              # low_cpu_mem_usage=True,
#                                              device_map="auto"
#                                             )



@spaces.GPU(duration=180)
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    input_text = [
        'What is the capital of United States?',
    ]

    input_tokens = model.tokenizer(input_text,
    return_tensors="pt", 
    return_attention_mask=False, 
    truncation=True, 
    max_length=MAX_LENGTH, 
    padding=True)
           
    generation_output = model.generate(
    input_tokens['input_ids'].cuda(), 
    max_new_tokens=20,
    use_cache=True,
    return_dict_in_generate=True)

    output = model.tokenizer.decode(generation_output.sequences[0])

    print(output)
    yield output
    
  
    messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

    # inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")

    # outputs = model.generate(inputs, max_new_tokens=2000)
    # gen_text=tokenizer.decode(outputs[0], skip_special_tokens=True)
   
    # 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()