Create app.py

app.py

@@ -0,0 +1,57 @@
+import transformers
+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()