README.md

metadata

language: en
license: mit
library_name: transformers
tags:
  - llama
  - llama-3
  - causal-lm
  - vllm
  - conversational
  - cognitive-therapy
  - mental-health
  - lora
  - peft
inference:
  parameters:
    max_new_tokens: 256
    temperature: 0.7
    top_p: 0.9
    repetition_penalty: 1.1
datasets:
  - Lumiiree/therapod-dpo
base_model:
  - meta-llama/Llama-3.2-3B-Instruct

🧠 CBT-Copilot

CBT-Copilot is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct, designed to simulate compassionate and supportive dialogues in the style of Cognitive Behavioral Therapy (CBT).

Fine-tuned using LoRA on the Lumiiree/therapod-dpo dataset and merged into a standalone model, it supports deployment through transformers, vLLM, and other inference frameworks.

---

🚀 How to Use (with vLLM)

Serve this model using vLLM:

pip install vllm[serve]

python3 -m vllm.entrypoints.openai.api_server --model thillaic/CBT-Copilot

Then query it via the OpenAI-compatible API:

import openai

openai.api_key = "EMPTY"
openai.api_base = "http://localhost:8000/v1"

response = openai.ChatCompletion.create(
    model="CBT-Copilot",
    messages=[
        {"role": "system", "content": "You are a compassionate CBT therapist."},
        {"role": "user", "content": "I've been feeling really anxious lately. What can I do?"}
    ]
)

print(response["choices"][0]["message"]["content"])

---

🧠 Intended Use

This model is intended for:

• Mental health chatbot research
• Journaling and self-reflection tools
• Prototyping conversational CBT agents

⚠️ Disclaimer: This model is not a replacement for licensed mental health professionals. It should only be used for educational, research, or prototyping purposes.

---

📜 License

Licensed under the MIT License.

---

🙏 Acknowledgements

• Based on Meta’s LLaMA 3.2B Instruct model
• Trained on Lumiiree/therapod-dpo
• Fine-tuning performed with Hugging Face transformers, PEFT, and LoRA

---

🛠️ Model developed by Thillai Chithambaram