Views
No views yet
1from llama_cpp import Llama
2
3llm = Llama.from_pretrained(
4 repo_id="MTSAIR/Cotype-Nano-GGUF",
5 filename="cotype_nano_8bit.gguf",
6)
7
8llm.create_chat_completion(
9 messages = [
10 {
11 "role": "user",
12 "content": "What is the capital of France?"
13 }
14 ]
15)