Fresh deploy with binaries and models via LFS

Dockerfile

@@ -0,0 +1,45 @@
+FROM php:8.2-cli
+
+# 1. Instalar dependencias del sistema y extensiones PHP
+# libgomp1 es vital para OpenMP (multithreading de llama.cpp)
+RUN apt-get update && apt-get install -y \
+    libcurl4 \
+    libgomp1 \
+    libzip-dev \
+    unzip \
+    git \
+    && docker-php-ext-install zip \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# 2. Instalar Composer
+COPY --from=composer:latest /usr/bin/composer /usr/bin/composer
+
+# 3. Copiar binarios pre-compilados y librerías
+COPY binaries/bin/* /usr/local/bin/
+COPY binaries/lib/* /usr/local/lib/
+# Actualizar el enlazador dinámico para que encuentre las libs en /usr/local/lib
+RUN ldconfig
+
+# 4. Configurar usuario no-root (Requerido por HF Spaces)
+RUN useradd -m -u 1000 user
+
+# 5. Preparar directorio de la aplicación
+WORKDIR /app
+RUN chown user:user /app
+
+# Cambiar a usuario
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# 6. Instalar la aplicación llama-php
+RUN git clone https://github.com/enacimie/llama-php . \
+    && composer install --no-dev --optimize-autoloader
+
+# 7. Copiar modelos locales (con permisos de usuario)
+COPY --chown=user:user models/ /app/models/
+
+# 8. Exponer puerto y ejecutar
+EXPOSE 7860
+CMD ["php", "-S", "0.0.0.0:7860", "-t", "web/"]

README.md

@@ -0,0 +1,63 @@
+---
+title: Llama Php Demo
+emoji: 🏆
+colorFrom: green
+colorTo: green
+sdk: docker
+pinned: false
+short_description: Llama-php Demo
+---
+
+# 🏆 Llama PHP Demo
+
+![Llama PHP](https://img.shields.io/badge/PHP-8.1%2B-777BB4?style=flat-square&logo=php)
+![License](https://img.shields.io/badge/License-MIT-green?style=flat-square)
+
+This Hugging Face Space demonstrates **[llama.php](https://github.com/enacimie/llama-php)**, a robust PHP wrapper for executing local Large Language Models using `llama.cpp` as the inference engine.
+
+## 🌟 About llama.php
+
+llama.php is a modular, and productive PHP wrapper that lets you run Large Language Models completely offline. With a clean API similar to OpenAI or Hugging Face but 100% self-contained, it brings the power of LLMs to PHP applications without external dependencies.
+
+## ✨ Features Demonstrated
+
+- **Local Inference**: Runs completely offline using CPU
+- **GGUF Support**: Works with quantized models (Q4_K_M, Q5_K_S, etc.)
+- **Chat Templates**: Includes templates for Qwen, Llama 3, Mistral, and more
+- **Text Generation**: Generate responses to prompts
+- **Embeddings**: Create vector embeddings from text
+- **JSON Output**: Force structured JSON output with schema validation
+- **Secure Execution**: Proper shell argument escaping to prevent injection
+
+## 🚀 How to Use This Demo
+
+1. **Text Generation**: Enter a prompt in the text box and click "Generate"
+2. **Chat Mode**: Start a conversation with the model in chat interface
+3. **Embedding Demo**: Convert text to vector embeddings
+4. **JSON Mode**: Generate structured JSON output based on a schema
+
+Adjust parameters like temperature, max tokens, and top-p to control the generation behavior.
+
+## ⚙️ Technical Details
+
+- **PHP Version**: 8.2
+- **Inference Engine**: llama.cpp
+- **Model**: Qwen3-0.6B-Q4_K_M (quantized for efficient CPU inference)
+- **Embedding Model**: Qwen3-Embedding-0.6B-Q4_K_M
+- **Docker Base**: Custom image with PHP 8.2 and llama.cpp binaries
+
+## 🤝 Credits
+
+This demo is powered by **[llama.php](https://github.com/enacimie/llama-php)** created by Eduardo Nacimiento-García.
+
+- **GitHub Repository**: https://github.com/enacimie/llama-php
+- **Original Models**: Qwen3 series from Alibaba
+- **Inference Backend**: https://github.com/ggerganov/llama.cpp
+
+## 📜 License
+
+This demo and the underlying llama.php library are released under the MIT License.
+
+---
+
+*Note: Due to resource limitations on Hugging Face Spaces, generation might be slower than on dedicated hardware. The model runs entirely on CPU with limited context window size.*

binaries/bin/llama-cli

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ffbbe9d3e860c632ab58eb69d4b9c5ea7060724bc682a74227ef02129f2916
+size 4352904

binaries/bin/llama-embedding

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a99c70b3d62004c2997e33386d8e956e622cc1bb150132017682ab0717b4fca
+size 3291224

binaries/lib/libggml-base.so

@@ -0,0 +1 @@
+libggml-base.so.0

binaries/lib/libggml-base.so.0

@@ -0,0 +1 @@
+libggml-base.so.0.9.4

binaries/lib/libggml-base.so.0.9.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065a3616ad3be7ebaa4156454163cbf12fa6e6e98c5c04a3a5a479253e7ca4a5
+size 694632

binaries/lib/libggml-cpu.so

@@ -0,0 +1 @@
+libggml-cpu.so.0

binaries/lib/libggml-cpu.so.0

@@ -0,0 +1 @@
+libggml-cpu.so.0.9.4

binaries/lib/libggml-cpu.so.0.9.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c8e44f06dfd329bba146a0bbbda8ec77fcbe95191f6c5ad7a203d75e7984de
+size 963592

binaries/lib/libggml.so

@@ -0,0 +1 @@
+libggml.so.0

binaries/lib/libggml.so.0

@@ -0,0 +1 @@
+libggml.so.0.9.4

binaries/lib/libggml.so.0.9.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5ebea3cd1243ab6a494c39285c52e3dafe1712aef9d2677d26ab440d084e16
+size 55712

binaries/lib/libllama.so

@@ -0,0 +1 @@
+libllama.so.0

binaries/lib/libllama.so.0

@@ -0,0 +1 @@
+libllama.so.0.0.7584

binaries/lib/libllama.so.0.0.7584

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efda5218094af8b4680aa20b6555b284755f414fd2e75e98731a0e25632317f0
+size 2872232

binaries/lib/libmtmd.so

@@ -0,0 +1 @@
+libmtmd.so.0

binaries/lib/libmtmd.so.0

@@ -0,0 +1 @@
+libmtmd.so.0.0.7584

binaries/lib/libmtmd.so.0.0.7584

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c4eaece54058b8c5bb1f8371d51e97017c5c0042aec57b1a5dece72022603b
+size 877448

models/qwen3-0.6b-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc0ee44eb39790624623cf5e2a8cc21973c4839a67fed406dd3f9b2e6b7f800
+size 484220160

models/qwen3-embedding-0.6b-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c3e3f2eaabc6e321702b4a13680d042e72afc5d602f359f27a670c3e54718c
+size 396474560