简介
Github仓库:
所有的博客都会发表在这里：
如：
API
以下我们展示了一段简短的示例代码，说明如何通过 API 使用 QwQ-32B:
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
from openai import OpenAI
import os
# Initialize OpenAI client
client = OpenAI(
# If the environment variable is not configured, replace with your API Key: api_key="sk-xxx"
# How to get an API Key：https://help.aliyun.com/zh/model-studio/developer-reference/get-api-key
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)
reasoning_content = ""
content = ""
is_answering = False
completion = client.chat.completions.create(
model="qwq-32b",
messages=[
{"role": "user", "content": "Which is larger, 9.9 or 9.11?"}
],
stream=True,
# Uncomment the following line to return token usage in the last chunk
# stream_options={
# "include_usage": True
# }
)
print("\n" + "=" * 20 + "reasoning content" + "=" * 20 + "\n")
for chunk in completion:
# If chunk.choices is empty, print usage
if not chunk.choices:
print("\nUsage:")
print(chunk.usage)
else:
delta = chunk.choices[0].delta
# Print reasoning content
if hasattr(delta, 'reasoning_content') and delta.reasoning_content is not None:
print(delta.reasoning_content, end='', flush=True)
reasoning_content += delta.reasoning_content
else:
if delta.content != "" and is_answering is False:
print("\n" + "=" * 20 + "content" + "=" * 20 + "\n")
is_answering = True
# Print content
print(delta.content, end='', flush=True)
content += delta.content
