app.py

"""
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
import os

access_token = os.environ['HF_TOKEN']

config = PeftConfig.from_pretrained("HiTZ/Mistral-7B-MedExpQA-EN")
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", token=access_token)
model = PeftModel.from_pretrained(model, "HiTZ/Mistral-7B-MedExpQA-EN", token=access_token)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", token=access_token)

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
"""
from huggingface_hub import InferenceClient
import gradio as gr
import os
access_token = os.environ['HF_TOKEN']

import requests

API_URL = "https://api-inference.huggingface.co/models/HiTZ/Mistral-7B-MedExpQA-EN"
headers = {"Authorization": "Bearer "+access_token}

def query(payload):
	response = requests.post(API_URL, headers=headers, json=payload)
	return response.json()
	
output = query({
	"inputs": "Can you please let us know more details about your ",
})

"""
client = InferenceClient("mistralai/Mistral-7B-v0.1",access_token)

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 = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    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",
    )
]


gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="Mistral 7B fine-tuned on MedExpQA with max RAG 32"
).launch(show_api=False)
"""