Instructions to use arti456789/ayurveda-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arti456789/ayurveda-chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="arti456789/ayurveda-chat")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("arti456789/ayurveda-chat") model = AutoModelForCausalLM.from_pretrained("arti456789/ayurveda-chat") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use arti456789/ayurveda-chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "arti456789/ayurveda-chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arti456789/ayurveda-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/arti456789/ayurveda-chat
- SGLang
How to use arti456789/ayurveda-chat with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "arti456789/ayurveda-chat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arti456789/ayurveda-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "arti456789/ayurveda-chat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arti456789/ayurveda-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use arti456789/ayurveda-chat with Docker Model Runner:
docker model run hf.co/arti456789/ayurveda-chat
Ayurveda Chat
Ayurveda Chat is a fine-tuned text-generation model designed to answer questions about Ayurveda in a simple, conversational, beginner-friendly way.
The model can help with general Ayurveda education, dosha explanations, Vata, Pitta, Kapha, Prakriti, Agni, digestion, daily routine, seasonal care, Panchakarma education, food guidance, sleep, skin care, hair care, and general wellness-style questions.
This model is intended for educational chatbot demos and general learning. It is not a medical professional and should not be used for diagnosis, treatment, or emergency care.
Model Overview
- Model ID:
arti456789/ayurveda-chat - Base model:
Qwen/Qwen2.5-1.5B - Task: Text generation / chat
- License: Apache 2.0
- Language: English
- Library: Transformers
Try the Demo
You can test the model in the browser through the Space:
Try in Google Colab
How to Use
Install Requirements
pip install transformers accelerate safetensors sentencepiece torch
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=180):
prompt = f"""System: You are a helpful Ayurveda education assistant. Answer in simple, clear, natural, beginner-friendly language. Stay educational and safe. Do not claim to cure serious diseases. For urgent symptoms, serious illness, pregnancy, child health, chronic disease, or medication questions, suggest a qualified healthcare professional.
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=1.12,
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?
- Compare Vata, Pitta, and Kapha.
- What is Prakriti in Ayurveda?
- What is Agni in Ayurveda?
- How does Ayurveda explain digestion?
- Is Panchakarma a simple home detox?
- What should I eat if my digestion is weak?
- Can Ayurveda cure diabetes?
- I have fever, what should I do?
- I want bright skin. What should I do?
- Give me simple daily routine tips from Ayurveda.
- What are common Vata imbalance signs?
- What are common Pitta imbalance signs?
- What are common Kapha imbalance signs?
Intended Use
This model is intended for:
- general Ayurveda Q&A
- simple explanatory responses
- educational chatbot demos
- beginner-friendly Ayurveda learning
- dosha explanation
- Vata, Pitta, and Kapha education
- Prakriti and Agni explanation
- wellness and lifestyle discussion
- conversational text-generation examples
Out-of-Scope Use
This model should not be used for:
- medical diagnosis
- emergency care
- replacing a doctor or qualified clinician
- prescribing herbs, medicines, or supplements
- treating serious disease
- pregnancy medical decisions
- child medical decisions
- medication interaction decisions
- emergency symptom evaluation
Limitations
- This model is not a medical professional.
- It should not be used for diagnosis, treatment, emergency care, or medical decision-making.
- It may give incorrect, incomplete, outdated, or oversimplified answers.
- It may sometimes generate confident-sounding but inaccurate information.
- It may not understand all medical conditions or personal health contexts.
- 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, fainting, confusion, high fever, severe dehydration, severe allergic reaction, or pregnancy-related complications, seek emergency medical care immediately.
For chronic illness, children, pregnancy, serious symptoms, medication questions, or supplement/herb use, consult a qualified healthcare professional before making health decisions.
Recommended System Prompt
For safer and more consistent responses, use this system prompt when running the model:
You are a helpful Ayurveda education assistant. Answer in simple, clear, natural, beginner-friendly language. Stay educational and safe. Do not claim to cure serious diseases. For urgent symptoms, serious illness, pregnancy, child health, chronic disease, or medication questions, suggest a qualified healthcare professional.
Training Notes
This repository contains the exported model files and tokenizer files for the fine-tuned Ayurveda chatbot.
The model was fine-tuned for conversational Ayurveda education, simple explanations, safety-aware answers, and beginner-friendly responses.
Files Included
config.jsonmodel.safetensorstokenizer.jsontokenizer_config.jsonspecial_tokens_map.jsonadded_tokens.jsonvocab.jsonmerges.txt
Citation
If you use this model, please cite the repository and the underlying base model.
- Model:
arti456789/ayurveda-chat - Base model:
Qwen/Qwen2.5-1.5B
Disclaimer
This model provides general educational information only. It does not provide medical advice, diagnosis, or treatment. Always consult a qualified healthcare professional for personal medical concerns.
- Downloads last month
- 39
Model tree for arti456789/ayurveda-chat
Base model
Qwen/Qwen2.5-1.5B