From 9327ac80df9a537bc9e14dc9ed2c0b36762e09cc Mon Sep 17 00:00:00 2001
From: Falko Habel <falko.habel@gmx.de>
Date: Tue, 11 Feb 2025 19:55:32 +0100
Subject: [PATCH] added usage example

---
 example.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100644 example.py

diff --git a/example.py b/example.py
new file mode 100644
index 0000000..ae3a35a
--- /dev/null
+++ b/example.py
@@ -0,0 +1,15 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+location = "Godala-moe"
+
+device = "cuda" # cpu when not using gpu
+tokenizer = AutoTokenizer.from_pretrained(location)
+
+model = AutoModelForCausalLM.from_pretrained(location).to(device)
+
+messages = [{"role": "user", "content": "What can you tell me about Godot?"}]
+input_text=tokenizer.apply_chat_template(messages, tokenize=False)
+inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
+outputs = model.generate(inputs, max_new_tokens=510, temperature=0.2, top_p=0.9, do_sample=True)
+print(tokenizer.decode(outputs[0]))