Add TeleChat-thinking API inference support

[ccx06]

[Feature] Add TeleChat-thinking API inference support

Motivation

This PR introduces an TeleChat-thinking client wrapper that enables the use of TeleChat models within OpenCompass.

Modification

1. API Integration for TeleChat-thinking

• Add API client code at opencompass/models/telechat_api/

• Add config files at opencompass/configs/models/telechat/

• Update model registry in opencompass/models/__init__.py

2. Evaluation Script for Academic Benchmarks

• Add examples/eval_academic_telechat_thinking.py to reproduce TeleChat's performance on academic leaderboards.

3. This modification does not affect or introduce any backward-incompatible changes to the downstream repositories.

Use cases (Optional)

export TeleChat_API_KEY="xxx"
export TeleChat_API_URL="yyy"
opencompass examples/eval_academic_telechat_thinking.py

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.

[ccx06]

@Myhs-phz Hi! We have received the check results, but we are unable to determine the reason for the pr_run_test / pr_run_test (pull_request) failure. Could you please help explain it? Thank you!

[Myhs-phz]

hi, @ccx06 . You only need to fix lint.

[ccx06]

hi, @ccx06 . You only need to fix lint.

Thank you very much for your help!