app.py

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, DataCollatorForSeq2Seq
from datasets import load_dataset, load_from_disk
from evaluate import load
import torch
import os

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="openaccess-ai-collective/minotaur-15b")
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/minotaur-15b")
model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/minotaur-15b")
model_id = "your_model_id"  # Replace with your model ID
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
data_collator = DataCollatorForSeq2Seq(tokenizer, model=model)

def generate_answer(question, file_path):
    if os.path.exists(file_path):
        # Load data from file
        if file_path.endswith(".csv"):
            data = pd.read_csv(file_path)
        elif file_path.endswith(".json"):
            data = json.load(open(file_path))
        else:
            data = open(file_path, "r").read()
    else:
        data = ""

    prompt = f"""
Answer the question based on the provided context:

Question: {question}

Context: {data}

Answer:
"""
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs.input_ids.to(torch.device("cuda" if torch.cuda.is_available() else "cpu"))
    attention_mask = inputs.attention_mask.to(torch.device("cuda" if torch.cuda.is_available() else "cpu"))
    output = model.generate(input_ids=input_ids, attention_mask=attention_mask)
    answer = tokenizer.decode(output[0], skip_special_tokens=True)
    return answer

def main():
    question = input("Enter your question: ")
    file_path = input("Enter the file path (optional): ")
    answer = generate_answer(question, file_path)
    print(f"Answer: {answer}")

if __name__ == "__main__":
    main()