Create README.md

Author: elGuille

README.md

@@ -0,0 +1,21 @@
+## Release v1.0 — tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
+
+A compact, quantized chat model file in GGUF format.
+
+### Contents
+- tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf — 1.1B-parameter chat model quantized to Q4_K_M for reduced size and faster inference.
+
+### Usage example (CLI)
+1. Download the GGUF file to your model directory.
+2. Load with a compatible runtime (example: llama.cpp / ggml-based runtimes):
+```
+./main -m ./models/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf -p "Hello, how are you?"
+```
+
+### Notes
+- Quantized format trades some precision for smaller size and speed — suitable for lightweight inference and experimentation.
+- Ensure your inference tool supports GGUF and the Q4_K_M quantization type.
+- No license or training data details included — check upstream/source for licensing and provenance.
+
+### Contact
+For issues or questions, open an issue on this repository.