forked from abetlen/llama-cpp-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_llama.py
More file actions
171 lines (131 loc) · 5.13 KB
/
test_llama.py
File metadata and controls
171 lines (131 loc) · 5.13 KB
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
import llama_cpp
MODEL = "./vendor/llama.cpp/models/ggml-vocab.bin"
def test_llama():
llama = llama_cpp.Llama(model_path=MODEL, vocab_only=True)
assert llama
assert llama.ctx is not None
text = b"Hello World"
assert llama.detokenize(llama.tokenize(text)) == text
# @pytest.mark.skip(reason="need to update sample mocking")
def test_llama_patch(monkeypatch):
llama = llama_cpp.Llama(model_path=MODEL, vocab_only=True)
n_vocab = llama_cpp.llama_n_vocab(llama.ctx)
## Set up mock function
def mock_eval(*args, **kwargs):
return 0
def mock_get_logits(*args, **kwargs):
return (llama_cpp.c_float * n_vocab)(
*[llama_cpp.c_float(0) for _ in range(n_vocab)]
)
monkeypatch.setattr("llama_cpp.llama_cpp.llama_eval", mock_eval)
monkeypatch.setattr("llama_cpp.llama_cpp.llama_get_logits", mock_get_logits)
output_text = " jumps over the lazy dog."
output_tokens = llama.tokenize(output_text.encode("utf-8"))
token_eos = llama.token_eos()
n = 0
def mock_sample(*args, **kwargs):
nonlocal n
if n < len(output_tokens):
n += 1
return output_tokens[n - 1]
else:
return token_eos
monkeypatch.setattr("llama_cpp.llama_cpp.llama_sample_token", mock_sample)
text = "The quick brown fox"
## Test basic completion until eos
n = 0 # reset
completion = llama.create_completion(text, max_tokens=20)
assert completion["choices"][0]["text"] == output_text
assert completion["choices"][0]["finish_reason"] == "stop"
## Test streaming completion until eos
n = 0 # reset
chunks = llama.create_completion(text, max_tokens=20, stream=True)
assert "".join(chunk["choices"][0]["text"] for chunk in chunks) == output_text
assert completion["choices"][0]["finish_reason"] == "stop"
## Test basic completion until stop sequence
n = 0 # reset
completion = llama.create_completion(text, max_tokens=20, stop=["lazy"])
assert completion["choices"][0]["text"] == " jumps over the "
assert completion["choices"][0]["finish_reason"] == "stop"
## Test streaming completion until stop sequence
n = 0 # reset
chunks = llama.create_completion(text, max_tokens=20, stream=True, stop=["lazy"])
assert (
"".join(chunk["choices"][0]["text"] for chunk in chunks) == " jumps over the "
)
assert completion["choices"][0]["finish_reason"] == "stop"
## Test basic completion until length
n = 0 # reset
completion = llama.create_completion(text, max_tokens=2)
assert completion["choices"][0]["text"] == " j"
assert completion["choices"][0]["finish_reason"] == "length"
## Test streaming completion until length
n = 0 # reset
chunks = llama.create_completion(text, max_tokens=2, stream=True)
assert "".join(chunk["choices"][0]["text"] for chunk in chunks) == " j"
assert completion["choices"][0]["finish_reason"] == "length"
def test_llama_pickle():
import pickle
import tempfile
fp = tempfile.TemporaryFile()
llama = llama_cpp.Llama(model_path=MODEL, vocab_only=True)
pickle.dump(llama, fp)
fp.seek(0)
llama = pickle.load(fp)
assert llama
assert llama.ctx is not None
text = b"Hello World"
assert llama.detokenize(llama.tokenize(text)) == text
def test_utf8(monkeypatch):
llama = llama_cpp.Llama(model_path=MODEL, vocab_only=True)
n_vocab = llama_cpp.llama_n_vocab(llama.ctx)
## Set up mock function
def mock_eval(*args, **kwargs):
return 0
def mock_get_logits(*args, **kwargs):
return (llama_cpp.c_float * n_vocab)(
*[llama_cpp.c_float(0) for _ in range(n_vocab)]
)
monkeypatch.setattr("llama_cpp.llama_cpp.llama_eval", mock_eval)
monkeypatch.setattr("llama_cpp.llama_cpp.llama_get_logits", mock_get_logits)
output_text = "😀"
output_tokens = llama.tokenize(output_text.encode("utf-8"))
token_eos = llama.token_eos()
n = 0
def mock_sample(*args, **kwargs):
nonlocal n
if n < len(output_tokens):
n += 1
return output_tokens[n - 1]
else:
return token_eos
monkeypatch.setattr("llama_cpp.llama_cpp.llama_sample_token", mock_sample)
## Test basic completion with utf8 multibyte
n = 0 # reset
completion = llama.create_completion("", max_tokens=4)
assert completion["choices"][0]["text"] == output_text
## Test basic completion with incomplete utf8 multibyte
n = 0 # reset
completion = llama.create_completion("", max_tokens=1)
assert completion["choices"][0]["text"] == ""
def test_llama_server():
from fastapi.testclient import TestClient
from llama_cpp.server.app import create_app, Settings
settings = Settings(
model=MODEL,
vocab_only=True,
)
app = create_app(settings)
client = TestClient(app)
response = client.get("/v1/models")
assert response.json() == {
"object": "list",
"data": [
{
"id": MODEL,
"object": "model",
"owned_by": "me",
"permissions": [],
}
],
}