feat: Adding open-r1/OlympicCoder-32B by HF to model list

[didier-durand]

Description

Describe your changes in detail (optional if the linked issue already contains a detailed description of the changes).

Checklist

Go over all the following points, and put an x in all the boxes that apply.

• [X ] I have read the CONTRIBUTION guide (required)
• [ ] I have linked this PR to an issue using the Development section on the right sidebar or by adding Fixes #issue-number in the PR description (required)
• [X ] I have checked if any dependencies need to be added or updated in pyproject.toml and uv lock
• [ ] I have updated the tests accordingly (required for a bug fix or a new feature)
• [ ] I have updated the documentation if needed:
• [ ] I have added examples if this is a new feature

I successfully tested open-r1/OlympicCoder-32B by HF with SGLang v0.4.4.post1

So, adding it to the list of models usable in Camel

For model details, see https://huggingface.co/blog/open-r1/update-3

[fengju0213]

thanks @ @didier-durand but adding a model requires more than just modifying this part. You can refer to [this commit](https://github.com/camel-ai/camel/commit/7402cb605189fc8565d7162f5e4c979871d344cd#diff-da12c62b6d52b37e1a57e53ff7f55439be624375e8da6183f83e28a710f8aa8e) for guidance.

[didier-durand]

Hi,

Olympic coder is a fine-tuning of Qwen2.5-Coder-32B-Instruct

From its README.md:

---
license: apache-2.0
datasets:
- open-r1/codeforces-cots
language:
- en
base_model:
- Qwen/Qwen2.5-Coder-32B-Instruct
pipeline_tag: text-generation
---

# Model Card for OlympicCoder-32B

OlympicCoder-32B is a code mode that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe 2024 International Olympiad in Informatics.

* Repository: https://github.com/huggingface/open-r1
* Blog post: https://huggingface.co/blog/open-r1/update-3

## Model description

- **Model type:** A 32B parameter model fine-tuned on a decontaminated version of the codeforces dataset.
- **Language(s) (NLP):** Primarily English
- **License:** apache-2.0
- **Finetuned from model:** [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)

So should I link Olympic Coder to page https://github.com/camel-ai/camel/blob/master/camel/configs/qwen_config.py to avoid repeating things already explained for Qwen ?

[fengju0213]

Hi,

Olympic coder is a fine-tuning of Qwen2.5-Coder-32B-Instruct

From its README.md:

---
license: apache-2.0
datasets:
- open-r1/codeforces-cots
language:
- en
base_model:
- Qwen/Qwen2.5-Coder-32B-Instruct
pipeline_tag: text-generation
---

# Model Card for OlympicCoder-32B

OlympicCoder-32B is a code mode that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe 2024 International Olympiad in Informatics.

* Repository: https://github.com/huggingface/open-r1
* Blog post: https://huggingface.co/blog/open-r1/update-3

## Model description

- **Model type:** A 32B parameter model fine-tuned on a decontaminated version of the codeforces dataset.
- **Language(s) (NLP):** Primarily English
- **License:** apache-2.0
- **Finetuned from model:** [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)

So should I link Olympic Coder to page https://github.com/camel-ai/camel/blob/master/camel/configs/qwen_config.py to avoid repeating things already explained for Qwen ?

If you want to use it in SGLANG, and SGLANG supports it, you can add it to SGLANG.

[didier-durand]

@fengju0213 : Hi Sun, yes, I use Olympic Coder with OWL on SGLang. So, opened a PR on SGLang project for this purpose: https://github.com/sgl-project/sglang/pull/4628. It's going to be merged soon

So, no need to reflect this on the Camel project?

[fengju0213]

sgl-project/sglang#4628

i see @didier-durand you can add it to camel after SGLang merge it and you should also modify the def is_sglang method

[fengju0213]

thanks @didier-durand

[zjrwtx]

thanks @didier-durand ,can this model support toolcalling?

[didier-durand]

Just to confirm the request of https://github.com/camel-ai/camel/pull/1929#issuecomment-2743995851 : https://github.com/sgl-project/sglang/pull/4628 has been merged

[didier-durand]

Re question https://github.com/camel-ai/camel/pull/1929#issuecomment-2760576549: Olympic Coder 32B comes from Qwen 2.5

See https://huggingface.co/open-r1/OlympicCoder-32B

As per https://qwen.readthedocs.io/en/latest/framework/function_call.html, Qwen models support function calling