File size: 1,323 Bytes
93adfea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2025 the LlamaFactory team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import os

from llamafactory.chat import ChatModel


TINY_LLAMA = os.getenv("TINY_LLAMA", "llamafactory/tiny-random-Llama-3")

INFER_ARGS = {
    "model_name_or_path": TINY_LLAMA,
    "finetuning_type": "lora",
    "template": "llama3",
    "infer_dtype": "float16",
    "do_sample": False,
    "max_new_tokens": 1,
}

MESSAGES = [
    {"role": "user", "content": "Hi"},
]

EXPECTED_RESPONSE = "_rho"


def test_chat():
    chat_model = ChatModel(INFER_ARGS)
    assert chat_model.chat(MESSAGES)[0].response_text == EXPECTED_RESPONSE


def test_stream_chat():
    chat_model = ChatModel(INFER_ARGS)
    response = ""
    for token in chat_model.stream_chat(MESSAGES):
        response += token

    assert response == EXPECTED_RESPONSE