怎么在本地命令行与导出的微调好的qwen2-2b-instruct模型进行多轮连贯视觉对话，给它图片，然后进行多轮对话

[audhuiaohduia]

Reminder

• I have read the README and searched the existing issues.

System Info

import os

from openai import OpenAI
from transformers.utils.versions import require_version

require_version("openai>=1.5.0", "To fix: pip install openai>=1.5.0")

def main():
client = OpenAI(
api_key="{}".format(os.environ.get("API_KEY", "0")),
base_url="http://localhost:{}/v1".format(os.environ.get("API_PORT", 8000)),
)
messages = []
messages.append(
{
"role": "user",
"content": [
{"type": "text", "text": "Output the color and number of each box."},
{
"type": "image_url",
"image_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/boxes.png"},
},
],
}
)
result = client.chat.completions.create(messages=messages, model="test")
messages.append(result.choices[0].message)
print("Round 1:", result.choices[0].message.content)
# The image shows a pyramid of colored blocks with numbers on them. Here are the colors and numbers of ...
messages.append(
{
"role": "user",
"content": [
{"type": "text", "text": "What kind of flower is this?"},
{
"type": "image_url",
"image_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/flowers.jpg"},
},
],
}
)
result = client.chat.completions.create(messages=messages, model="test")
messages.append(result.choices[0].message)
print("Round 2:", result.choices[0].message.content)
# The image shows a cluster of forget-me-not flowers. Forget-me-nots are small ...

if name == "main":
main()

Reproduction

import os

from openai import OpenAI
from transformers.utils.versions import require_version

require_version("openai>=1.5.0", "To fix: pip install openai>=1.5.0")

def main():
client = OpenAI(
api_key="{}".format(os.environ.get("API_KEY", "0")),
base_url="http://localhost:{}/v1".format(os.environ.get("API_PORT", 8000)),
)
messages = []
messages.append(
{
"role": "user",
"content": [
{"type": "text", "text": "Output the color and number of each box."},
{
"type": "image_url",
"image_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/boxes.png"},
},
],
}
)
result = client.chat.completions.create(messages=messages, model="test")
messages.append(result.choices[0].message)
print("Round 1:", result.choices[0].message.content)
# The image shows a pyramid of colored blocks with numbers on them. Here are the colors and numbers of ...
messages.append(
{
"role": "user",
"content": [
{"type": "text", "text": "What kind of flower is this?"},
{
"type": "image_url",
"image_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/flowers.jpg"},
},
],
}
)
result = client.chat.completions.create(messages=messages, model="test")
messages.append(result.choices[0].message)
print("Round 2:", result.choices[0].message.content)
# The image shows a cluster of forget-me-not flowers. Forget-me-nots are small ...

if name == "main":
main()

Expected behavior

import os

from openai import OpenAI
from transformers.utils.versions import require_version

require_version("openai>=1.5.0", "To fix: pip install openai>=1.5.0")

def main():
client = OpenAI(
api_key="{}".format(os.environ.get("API_KEY", "0")),
base_url="http://localhost:{}/v1".format(os.environ.get("API_PORT", 8000)),
)
messages = []
messages.append(
{
"role": "user",
"content": [
{"type": "text", "text": "Output the color and number of each box."},
{
"type": "image_url",
"image_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/boxes.png"},
},
],
}
)
result = client.chat.completions.create(messages=messages, model="test")
messages.append(result.choices[0].message)
print("Round 1:", result.choices[0].message.content)
# The image shows a pyramid of colored blocks with numbers on them. Here are the colors and numbers of ...
messages.append(
{
"role": "user",
"content": [
{"type": "text", "text": "What kind of flower is this?"},
{
"type": "image_url",
"image_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/flowers.jpg"},
},
],
}
)
result = client.chat.completions.create(messages=messages, model="test")
messages.append(result.choices[0].message)
print("Round 2:", result.choices[0].message.content)
# The image shows a cluster of forget-me-not flowers. Forget-me-nots are small ...

if name == "main":
main()

Others

给出的test_image可以进行一轮对话，怎么进行多轮呢，可以给出示例吗