Add lmdeploy tis python backend model

[ispobock]

Motivation

Propose evaluation code for LMDeploy TIS Python backend.

Modification

Add evaluation model and config files.

Use cases

python run.py configs/eval_internlm_chat_lmdeploy_tis.py -w outputs

Checklist

Before PR:

• Pre-commit or other linting tools are used to fix the potential lint issues.
• Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
• The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
• The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

• If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects.
• CLA has been signed and all committers have signed the CLA in this PR.

[ispobock]

@lvhan028 @Leymore Could you help review?

[ispobock]

Hi @lvhan028, this is the evaluation code for TIS python backend. Shall we add it here?

[lvhan028]

Hi @lvhan028, this is the evaluation code for TIS python backend. Shall we add it here?

yes. I'll review it tomorrow. Thanks a lot

[tonysy]

Hi @lvhan028, this is the evaluation code for TIS python backend. Shall we add it here?

yes. I'll review it tomorrow. Thanks a lot

@lvhan028 Can we merge this PR currently?

[lvhan028]

Oh, sorry.
My bad. I am going to review it right now

[lvhan028]

LGTM @tonysy
Thanks a lot @ispobock and sorry for the late response

[ispobock]

Hi @tonysy Could you help merge this PR?

[tonysy]

LGTM.
Also it would be great if you can update the documentation .

[tonysy]

Would you like to update the documentation to prodive more introduction of different backend? @ispobock @lvhan028

[ispobock]

@lvhan028 Shall we add a note for this backend here?

opencompass/docs/en/advanced_guides/evaluation_turbomind.md

Line 78 in 8fe7b27

- If you evaluate the InternLM 7B model, please modify `eval_internlm_turbomind.py` or `eval_internlm_chat_turbomind.py` by changing to the setting `models = [internlm_7b]` in the last line.