Update readme.

README.md

@@ -1,3 +1,28 @@
----
-license: bigscience-openrail-m
----
+# Refact-1.6B-fim-GGUF
+- Model creator: [Small Magellanic Cloud AI](https://huggingface.co/smallcloudai)
+- Original model: [Refact-1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim)
+
+
+## Description
+This repository contains quantized GGUF format model files for [Refact-1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim).
+
+
+## Prompt: fill in the middle
+```
+<fim_prefix>def print_hello_world():\n    """<fim_suffix>\n    print("Hello world!")<fim_middle>
+```
+
+
+## Prompt: chat (experimental)
+```
+<empty_output>SYSTEM You are a programming assistant
+<empty_output>USER How do I sort a list in Python?
+<empty_output>ASSISTANT
+```
+
+
+## Example `llama.cpp` command
+```shell
+./main -m refact-1_6b-Q4_K_M.gguf -c 4096 -n -1 -p '<fim_prefix>{prefix}<fim_suffix>{suffix}<fim_middle>'
+```
+For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)