metadata

license: apache-2.0
tags:
  - hindi
  - chatbot
  - question-answering
  - prakriti
  - flan-t5

Prakriti AI — A Hindi Question-Answering Model

Prakriti-AI is a custom-trained language model based on flan-t5-small, fine-tuned on over 10,000 Hindi question-answer pairs.
It is designed to understand and respond to Hindi queries in a natural, human-like way.

✨ Features

Base Model: google/flan-t5-small
Language: Hindi (and Hinglish supported)
Purpose: Q&A chatbot assistant
Trained by: Asankhla01
Use-case: Chatbots, education, AI assistants

🔧 Example Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model = AutoModelForSeq2SeqLM.from_pretrained("Asankhla01/prakriti-ai-model")
tokenizer = AutoTokenizer.from_pretrained("Asankhla01/prakriti-ai-model")

def ask_prakriti(question):
    input_text = "Q: " + question
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs)
    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return answer

ask_prakriti("AI kya hota hai?")

---
library_name: transformers
tags: []
---