Update README.md

README.md

@@ -15,17 +15,17 @@ pipeline_tag: text-generation
 
 <!--
 GHOSTAI • HORROR GGUF (7B)
-Professional HF README for a GGUF release (quantized only).
+Professional Hugging Face README for a quantized-only GGUF release.
 -->
 
 <p align="center">
-  <img src="https://capsule-render.vercel.app/api?type=waving&color=0:0b0b0f,50:2b0a2a,100:0b0b0f&height=160&section=header&text=GHOSTAI%20%E2%80%94%20HORROR%20GGUF%20(7B)&fontSize=44&fontColor=EAEAEA&animation=twinkling" />
+  <img src="https://capsule-render.vercel.app/api?type=waving&color=0:0b0b0f,50:2b0a2a,100:0b0b0f&height=160&section=header&text=GHOSTAI%20—%20HORROR%20GGUF%20(7B)&fontSize=44&fontColor=EAEAEA&animation=twinkling" />
 </p>
 
 <p align="center">
-  <img alt="GGUF" src="https://img.shields.io/badge/Format-GGUF-8A2BE2?style=for-the-badge">
+  <img alt="Format" src="https://img.shields.io/badge/Format-GGUF-8A2BE2?style=for-the-badge">
   <img alt="Runtime" src="https://img.shields.io/badge/Runtime-llama.cpp-5B2C83?style=for-the-badge">
-  <img alt="Size" src="https://img.shields.io/badge/Size-7B-3A0CA3?style=for-the-badge">
+  <img alt="Model Size" src="https://img.shields.io/badge/Model-7B-3A0CA3?style=for-the-badge">
   <img alt="Theme" src="https://img.shields.io/badge/Theme-Horror-8B0000?style=for-the-badge">
   <a href="https://www.linkedin.com/in/ccengineering/">
     <img alt="LinkedIn" src="https://img.shields.io/badge/LinkedIn-ccengineering-0A66C2?style=for-the-badge&logo=linkedin&logoColor=white">
@@ -33,16 +33,25 @@ Professional HF README for a GGUF release (quantized only).
 </p>
 
 <p align="center">
-  <b>GHOSTAI</b> is my first public model release: a <b>horror-themed 7B</b> model exported as <b>quantized GGUF</b> for the <b>llama.cpp</b> ecosystem.<br/>
-  <sub>Quantized-only release (no FP16 weights included).</sub>
+  <strong>GHOSTAI — HORROR GGUF (7B)</strong><br/>
+  A focused, horror-themed 7B model released exclusively in quantized GGUF format for the <strong>llama.cpp</strong> ecosystem.<br/>
+  <sub>Quantized-only release. No FP16 weights included.</sub>
 </p>
 
 ---
 
 ## Overview
 
-This repository provides multiple GGUF quantizations so you can choose the best balance of quality, speed, and memory for your setup.  
-It runs on **CPU-only** or with **GPU offload** (CUDA build of llama.cpp). Quant format is independent from CPU/GPU.
+**GHOSTAI** is a compact, atmosphere-driven horror model designed for narrative generation, roleplay, and dark storytelling.  
+It prioritizes tone, pacing, and vivid imagery over generic assistant behavior.
+
+This repository provides **multiple GGUF quantizations**, allowing you to choose the best balance of quality, speed, and memory usage for your hardware.
+
+The model runs:
+- Fully on **CPU**
+- With optional **GPU offload** (CUDA / Metal / Vulkan builds of llama.cpp)
+
+Quantization choice is independent of whether you use CPU or GPU.
 
 ---
 
@@ -68,7 +77,7 @@ Notes:
 
 ---
 
-## Recommended downloads
+## Recommended Downloads
 
 - Best default: **`Q4_K_M`**
 - More quality (more RAM): **`Q5_K_M`**, **`Q6_K`**, **`Q8_0`**
@@ -79,11 +88,11 @@ Notes:
 
 ## Quickstart (llama.cpp)
 
-### GPU offload (NVIDIA CUDA build)
+### 1) Run on CPU
 
 ```bash
 ./llama-cli \
   -m ghostai-horror-7b.Q4_K_M.gguf \
-  -ngl 99 \
   -c 4096 \
+  -t 8 \
   -p "You are GHOSTAI. Speak like a calm horror narrator. Keep it tight and vivid."