BUG: fix embedding model gte-Qwen2 dimensions

[JinCheng666]

Fixes #2471
fix embedding model gte-Qwen2 dimensions

wrong dimensions：

https://github.com/xorbitsai/inference/blob/48a07e8af3d015908c8a55f91c7baea3afbbb809/xinference/model/embedding/model_spec.json#L236C1-L237C1

correct dimensions：

inference/xinference/model/embedding/model_spec_modelscope.json

Line 238 in 48a07e8

"dimensions": 4096,

base on the right message：
https://huggingface.co/Alibaba-NLP/gte-Qwen1.5-7B-instruct
https://modelscope.cn/models/iic/gte_Qwen1.5-7B-instruct/summary

[JinCheng666]

right

[JinCheng666]

I don't know if this PR conforms to the project rules, please point out if there is anything wrong

[JinCheng666]

i dont know why the python3.11 check fail. it seems like not problems with the code.
how to rerun the checks? @qinxuye

[qinxuye]

i dont know why the python3.11 check fail. it seems like not problems with the code. how to rerun the checks? @qinxuye

That's OK, can you run python doc/source/gen_docs.py?

This will change many files, you can revert others but the gte-qwen2.rst then commit.

https://github.com/xorbitsai/inference/blob/main/doc/source/models/builtin/embedding/gte-qwen2.rst

[JinCheng666]

i dont know why the python3.11 check fail. it seems like not problems with the code. how to rerun the checks? @qinxuye

That's OK, can you run python doc/source/gen_docs.py?

This will change many files, you can revert others but the gte-qwen2.rst then commit.

https://github.com/xorbitsai/inference/blob/main/doc/source/models/builtin/embedding/gte-qwen2.rst

I ran the code locally and got an error, so I manually adjusted the contents of the file, not sure if it was appropriate？

window pc，The error information is as follows：

PS D:\work\code\inference\doc\source> python .\gen_docs.py
Traceback (most recent call last):
  File "D:\work\code\inference\doc\source\gen_docs.py", line 284, in <module>
    main()
  File "D:\work\code\inference\doc\source\gen_docs.py", line 54, in main
    models = json.load(model_file)
  File "C:\Users\liujincheng\.conda\envs\openaitest\lib\json\__init__.py", line 293, in load
    return loads(fp.read(),
UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 7227: illegal multibyte sequence

[qinxuye]

i dont know why the python3.11 check fail. it seems like not problems with the code. how to rerun the checks? @qinxuye

That's OK, can you run python doc/source/gen_docs.py?
This will change many files, you can revert others but the gte-qwen2.rst then commit.
https://github.com/xorbitsai/inference/blob/main/doc/source/models/builtin/embedding/gte-qwen2.rst

I ran the code locally and got an error, so I manually adjusted the contents of the file, not sure if it was appropriate？

window pc，The error information is as follows：

PS D:\work\code\inference\doc\source> python .\gen_docs.py
Traceback (most recent call last):
  File "D:\work\code\inference\doc\source\gen_docs.py", line 284, in <module>
    main()
  File "D:\work\code\inference\doc\source\gen_docs.py", line 54, in main
    models = json.load(model_file)
  File "C:\Users\liujincheng\.conda\envs\openaitest\lib\json\__init__.py", line 293, in load
    return loads(fp.read(),
UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 7227: illegal multibyte sequence

Should be OK, let's wait for CI to complete.

[JinCheng666]

i dont know why the python3.11 check fail. it seems like not problems with the code. how to rerun the checks? @qinxuye

That's OK, can you run python doc/source/gen_docs.py?
This will change many files, you can revert others but the gte-qwen2.rst then commit.
https://github.com/xorbitsai/inference/blob/main/doc/source/models/builtin/embedding/gte-qwen2.rst

I ran the code locally and got an error, so I manually adjusted the contents of the file, not sure if it was appropriate？
window pc，The error information is as follows：

PS D:\work\code\inference\doc\source> python .\gen_docs.py
Traceback (most recent call last):
  File "D:\work\code\inference\doc\source\gen_docs.py", line 284, in <module>
    main()
  File "D:\work\code\inference\doc\source\gen_docs.py", line 54, in main
    models = json.load(model_file)
  File "C:\Users\liujincheng\.conda\envs\openaitest\lib\json\__init__.py", line 293, in load
    return loads(fp.read(),
UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 7227: illegal multibyte sequence

Should be OK, let's wait for CI to complete.

so cool, my first pr is coming soon...

[qinxuye]

LGTM, thanks for your contribution!

[JinCheng666]

LGTM, thanks for your contribution!

thank you vary much ! happy 1024 day！ @qinxuye