Update README.md

README.md

@@ -1,20 +1,20 @@
 ---
-license: mit
-datasets:
-- Lumiiree/therapod-dpo
-language:
-- en
-base_model:
-- meta-llama/Llama-3.2-3B-Instruct
 tags:
 - llama
-- cbt
-- therapy
-- lora
-- qlora
-- casual-lm
+- llama-3
 - vllm
+- causal-lm
+- cognitive-therapy
+- mental-health
+- conversational
+- peft
+- lora
+license: mit
+datasets:
+- Lumiiree/therapod-dpo
+inference: true
 ---
+
 # 🧠 CBT-Copilot: LLaMA 3.2B Fine-Tuned for Cognitive Therapy
 
 Welcome to **CBT-Copilot**, an open-source LLM fine-tuned on therapy-aligned dialogues using the [Lumiiree/therapod-dpo](https://huggingface.co/datasets/Lumiiree/therapod-dpo) dataset. This model is designed to act as a **compassionate and supportive AI assistant**, trained in the tone of cognitive behavioral therapy (CBT), and suitable for mental health support applications.
@@ -104,6 +104,40 @@ print(response[0]['generated_text'])
 
 ---
 
+## ⚡ Inference with vLLM
+
+This model is **compatible with [vLLM](https://github.com/vllm-project/vllm)** — a fast and memory-efficient inference engine for LLMs.
+
+### 🚀 Quick Start with vLLM
+
+```bash
+pip install "vllm[serve]"
+
+python -m vllm.entrypoints.api_server \
+    --model thillaic/CBT-Copilot
+```
+
+### OpenAI-Compatible API Example
+
+```python
+import openai
+
+openai.api_base = "http://localhost:8000/v1"
+openai.api_key = "EMPTY"  # not needed for local use
+
+response = openai.ChatCompletion.create(
+    model="thillaic/CBT-Copilot",
+    messages=[
+        {"role": "system", "content": "You are a compassionate CBT therapist."},
+        {"role": "user", "content": "I'm feeling anxious lately. What should I do?"}
+    ]
+)
+
+print(response.choices[0].message["content"])
+```
+
+---
+
 ## 🧾 License
 
 This project is open-sourced for educational and research purposes under the **MIT License**.
@@ -125,4 +159,4 @@ This project is open-sourced for educational and research purposes under the **M
 
 ---
 
-*Crafted with care by Thillai Chithambaram for the future of compassionate AI.*
+*Crafted with care by Thillai Chithambaram for the future of compassionate AI.*