File size: 1,295 Bytes
b2ea2b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
import { describe, expect, it } from "vitest";
import type { ModelData } from "./model-data.js";
import { llama_cpp_python } from "./model-libraries-snippets.js";

describe("model-libraries-snippets", () => {
	it("llama_cpp_python conversational", async () => {
		const model: ModelData = {
			id: "bartowski/Llama-3.2-3B-Instruct-GGUF",
			pipeline_tag: "text-generation",
			tags: ["conversational"],
			inference: "",
		};
		const snippet = llama_cpp_python(model);

		expect(snippet.join("\n")).toEqual(`# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/Llama-3.2-3B-Instruct-GGUF",
	filename="{{GGUF_FILE}}",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)`);
	});

	it("llama_cpp_python non-conversational", async () => {
		const model: ModelData = {
			id: "mlabonne/gemma-2b-GGUF",
			tags: [""],
			inference: "",
		};
		const snippet = llama_cpp_python(model);

		expect(snippet.join("\n")).toEqual(`# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mlabonne/gemma-2b-GGUF",
	filename="{{GGUF_FILE}}",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)`);
	});
});