Add model card

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- llama
+- gguf
+- quantized
+library_name: transformers
+---
+
+# TinyLlama PHP Fine-tuned GGUF
+
+This is a GGUF conversion of the TinyLlama model fine-tuned for PHP code generation.
+
+## Model Details
+- **Base Model**: TinyLlama
+- **Fine-tuned for**: PHP code generation
+- **Format**: GGUF (quantized to q4_0)
+- **Use with**: llama.cpp, Ollama, or other GGUF-compatible inference engines
+
+## Usage
+
+### With llama.cpp:
+```bash
+./main -m model.gguf -p "Write a PHP function to"
+```
+
+### With Ollama:
+1. Create a Modelfile:
+```
+FROM ./model.gguf
+```
+2. Create the model:
+```bash
+ollama create tinyllama-php -f Modelfile
+ollama run tinyllama-php
+```