piyushgaba07/MAYA_Llama_2_7b_quantized_model

🧠 LLaMA 2 7B - Mental Therapy (Quantized, Instruction-Tuned)

Welcome to the repository for the LLaMA 2 7B Mental Therapy Quantized model — a safe and supportive conversational AI fine-tuned on mental health and therapy-related dialogues. Built on Meta’s LLaMA 2 7B, this model has been trained to generate empathetic, context-aware, and non-judgmental responses for users seeking emotional support and motivation.

⚠️ This model is not a replacement for professional mental health care. Use responsibly and always consult a licensed expert in case of serious mental health concerns.

---

💡 Model Highlights

• 🔧 Base model: meta-llama/Llama-2-7b-hf
• 🧠 Fine-tuning objective: Mental health and supportive conversation
• 🧱 Quantization: 4-bit (QLoRA) using bitsandbytes
• 🧾 Instruction format: Chat-like structure with ### User and ### Assistant prompts
• 🔐 Safe & empathetic responses: Fine-tuned with filtered mental health-related corpora
• 🚫 Very low toxicity: Evaluated with Detoxify and manual audits

---

🧪 Intended Use

This model is ideal for:

• Emotional wellness chatbots
• AI journaling assistants
• Motivational and CBT-style coaching tools
• Empathetic conversational agents for non-critical use

It is not suitable for:

• Diagnosing or treating mental illnesses
• Emergency or crisis intervention
• Replacing human therapists or counselors

---

🚀 How to Use

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "your-username/llama-2-7b-mental-therapy-quantized"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.float16
)

prompt = """### User: I'm feeling overwhelmed and anxious all the time. What should I do?
### Assistant:"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(response)