Update README.md

README.md

@@ -1,3 +1,38 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+
+# Simultaneous Machine Translation between English and Estonian using Llama-3.2
+
+## Introduction
+
+This is a llama-3.2 3B instruct model finetuned on TED20 subset of `et-ee` language pair. This subset contains 23k pair of sentences, half of which are trained as Estonian to English direction, while the other half are trained as English to Estonian direcion. This model is very good at translating in simultaneous manner, i.e. it can handle incomplete and streaming inputs.
+
+## How to run it
+
+First, install `llama.cpp`, follow https://github.com/ggerganov/llama.cpp?tab=readme-ov-file
+
+Then, pull the quantized gguf file, and run the following command:
+
+#### Estonian to English direction
+
+```bash
+llama-cli -m Llama-3.2-3B-Instruct-Q4_K_M.gguf -p "You are a professional Estonian-to-English simultaneous interpreter. Translate the following conversations into English." -cnv --chat-template llama3 -c 4096
+```
+
+#### English to Estonian direction
+
+change the system above to "You are a professional English-to-Estonian simultaneous interpreter. Translate the following conversations into Estonian.", i.e.
+
+```bash
+llama-cli -m Llama-3.2-3B-Instruct-Q4_K_M.gguf -p "You are a professional English-to-Estonian simultaneous interpreter. Translate the following conversations into Estonian." -cnv --chat-template llama3 -c 4096
+```
+
+
+
+Now you can try to type in sentences that you want to translate.
+
+- You may try to type in a few words, hit enter, and repeat. The model should be able to translate as you go.
+- You can also try to input a full sentence.
+- It's not great for a paragraph (yet).
+