app.py

from huggingface_hub import InferenceClient
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, AutoModel
from peft import PeftModel
import torch
# load base model
base_model = "mistralai/Mistral-7B-Instruct-v0.1"

#bnb_config = BitsAndBytesConfig(  
#    load_in_4bit= True,
#    bnb_4bit_quant_type= "nf4",
#    bnb_4bit_compute_dtype= torch.bfloat16,
#    bnb_4bit_use_double_quant= False,
#)

model = AutoModelForCausalLM.from_pretrained(
    base_model,
#    quantization_config=bnb_config,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

model.config.use_cache = True # silence the warnings. Please re-enable for inference!
model.config.pretraining_tp = 1
model.gradient_checkpointing_enable()

# load fine-tuned model
ft_model = PeftModel.from_pretrained(model, "gildead/mistral_7b_AES_v2_epoch")
ft_model.eval()


# load tokenizer 
tokenizer = AutoTokenizer.from_pretrained(ft_model, trust_remote_code=True)


prompt = "How do I find true love?"
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=3500)
result = pipe(f"<s>[INST] {prompt} [/INST]", max_new_tokens=7)
print(result[0]['generated_text'])



def format_prompt(message, history):
  prompt = "<s>"
  for user_prompt, bot_response in history:
    prompt += f"[INST] {user_prompt} [/INST]"
    prompt += f" {bot_response}</s> "
  prompt += f"[INST] {message} [/INST]"
  return prompt

def generate(
    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(prompt, history)

    stream = pipe(f"<s>[INST] {prompt} [/INST]")
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output


additional_inputs=[
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=1048,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

css = """
  #mkd {
    height: 500px; 
    overflow: auto; 
    border: 1px solid #ccc; 
  }
"""

with gr.Blocks(css=css) as demo:
    gr.HTML("<h1><center>Mistral 7B Instruct<h1><center>")
    gr.HTML("<h3><center>In this demo, you can chat with <a href='https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1'>Mistral-7B-Instruct</a> model. 💬<h3><center>")
    gr.HTML("<h3><center>Learn more about the model <a href='https://huggingface.co/docs/transformers/main/model_doc/mistral'>here</a>. 📚<h3><center>")
    gr.ChatInterface(
        generate,
        additional_inputs=additional_inputs,
        examples=[["What is the secret to life?"], ["Write me a recipe for pancakes."]]
    )

demo.queue(max_size=100).launch(max_threads=75,debug=True)