Ayurveda Chat

Ayurveda Chat is a fine-tuned text-generation model designed to answer questions about Ayurveda in a simple, conversational way.

Model Overview

  • Model ID: arti456789/ayurveda-chat
  • Base model: Qwen/Qwen2.5-1.5B
  • Task: Text generation / chat
  • License: Apache 2.0
  • Language: English

Try the Demo

You can test the model in the browser through the Space:

Open Ayurveda Chat Space

Try in Google Colab

!Open In Colab

How to Use

With Transformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo_id = "arti456789/ayurveda-chat"

tokenizer = AutoTokenizer.from_pretrained(repo_id, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto" if torch.cuda.is_available() else None,
)
model.eval()

def ask_model(question, max_new_tokens=128):
    prompt = f"""System: You are a helpful assistant. Answer the user's question clearly and safely.

User: {question}
Assistant:"""

    inputs = tokenizer(prompt, return_tensors="pt")
    if torch.cuda.is_available():
        inputs = {k: v.to(model.device) for k, v in inputs.items()}

    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=max_new_tokens,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
            repetition_penalty=1.1,
            pad_token_id=tokenizer.eos_token_id,
        )

    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return text.split("Assistant:")[-1].strip()

print(ask_model("What is Vata dosha?"))

Example Prompts

  • What is Ayurveda?
  • What is Vata dosha?
  • What are the three doshas?
  • What is Prakriti in Ayurveda?
  • How does Ayurveda explain digestion?
  • What is Agni in Ayurveda?

Intended Use

This model is intended for:

  • general Ayurveda Q&A
  • simple explanatory responses
  • educational chatbot demos

Limitations

  • This model is not a medical professional.
  • It should not be used for diagnosis or emergency care.
  • It may give incorrect or oversimplified answers.
  • Always verify important health information with a qualified clinician.

Safety Note

If you have urgent symptoms such as chest pain, breathing difficulty, sudden weakness, severe bleeding, or confusion, seek emergency medical care immediately.

Training Notes

This repository contains the exported model files and tokenizer files for the fine-tuned Ayurveda chatbot.

Files Included

  • config.json
  • model.safetensors
  • tokenizer.json
  • tokenizer_config.json
  • special_tokens_map.json
  • added_tokens.json
  • vocab.json
  • merges.txt

Citation

If you use this model, please cite the repository and the underlying base model.

Downloads last month
18
Safetensors
Model size
2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 2 Ask for provider support

Model tree for arti456789/ayurveda-chat

Finetuned
(349)
this model

Space using arti456789/ayurveda-chat 1