Point app to org model repo

README.md

@@ -12,7 +12,7 @@ header: mini
 short_description: "Dense Gradio lab console for probing a Phase-3 Q8 GGUF."
 suggested_hardware: zero-a10g
 models:
-  - owenisas/phase-3-gguf
+  - build-small-hackathon/phase-3-gguf
 tags:
   - gradio
   - zerogpu
@@ -27,7 +27,7 @@ license: mit
 # First-Principle AI
 
 First-Principle AI is a compact Gradio console for probing the
-`owenisas/phase-3-gguf` Q8 GGUF model through
+`build-small-hackathon/phase-3-gguf` Q8 GGUF model through
 `llama-cpp-python`.
 
 The UI is intentionally dense: chat, sampling controls, system prompt,
@@ -36,7 +36,7 @@ one screen.
 
 ## Runtime Notes
 
-- Model repo: `owenisas/phase-3-gguf`
+- Model repo: `build-small-hackathon/phase-3-gguf`
 - Model file: `model-Q8_0.gguf`
 - Runtime: `llama-cpp-python`
 - Hardware target: ZeroGPU

app.py

@@ -25,7 +25,7 @@ else:
     LLAMA_IMPORT_ERROR = None
 
 
-MODEL_REPO = os.getenv("PHASE3_MODEL_REPO", "owenisas/phase-3-gguf")
+MODEL_REPO = os.getenv("PHASE3_MODEL_REPO", "build-small-hackathon/phase-3-gguf")
 MODEL_FILE = os.getenv("PHASE3_MODEL_FILE", "model-Q8_0.gguf")
 MODEL_LABEL = "First-Principle AI"
 LOCAL_MODEL_PATH = Path("/Users/user/.lmstudio/models/owenisas/Phase-3-GGUF/model-Q8_0.gguf")
@@ -424,7 +424,7 @@ with gr.Blocks(title="First-Principle AI", fill_width=True) as demo:
               <h1>First-Principle AI</h1>
               <p>A dense Gradio console for probing the Phase-3 Q8 GGUF with visible runtime diagnostics.</p>
               <div class="phase-badge-row">
-                <span class="phase-badge"><strong>Model</strong> owenisas/phase-3-gguf</span>
+                <span class="phase-badge"><strong>Model</strong> build-small-hackathon/phase-3-gguf</span>
                 <span class="phase-badge"><strong>Runtime</strong> llama.cpp via llama-cpp-python</span>
                 <span class="phase-badge"><strong>Hardware target</strong> ZeroGPU with guarded fallback</span>
               </div>