Tianxing Yang
Tianxing Yang
> it is the repo of qwen2.5-coder, maybe you should submit your issue to ds-coder? @cyente What "ds-coder" are you referring to? Thanks.
> @ytxmobile98 I think you need to set the `--max-model-len` to a larger number, like 8192. BTW, you may check the log file to locate the issues. Looks like `--max-model-len`...
# Update 2024-12-11 @cyente @Hambaobao I have done some further work in the past two days, testing the [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) model and the [DeepSeek-Coder-6.7B-Instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) model, and found one key cause: The...
# Attachments ## The minimal dataset to test (5 examples) [humaneval_java.jsonl.txt](https://github.com/user-attachments/files/17518728/humaneval_java.jsonl.txt) ## First evaluation [result_humaneval_java.jsonl.bak.txt](https://github.com/user-attachments/files/17518737/result_humaneval_java.jsonl.bak.txt) [result_humaneval_java_evaluation_result.jsonl.bak.txt](https://github.com/user-attachments/files/17518753/result_humaneval_java_evaluation_result.jsonl.bak.txt) ## Second evaluation [result_humaneval_java.jsonl.txt](https://github.com/user-attachments/files/17518745/result_humaneval_java.jsonl.txt) [result_humaneval_java_evaluation_result.jsonl.txt](https://github.com/user-attachments/files/17518757/result_humaneval_java_evaluation_result.jsonl.txt)
> it is weired, let me try the samples @cyente Did you see anything unusual as you tried out?
> maybe is's about ""? I think it might be . Oh yes. Thanks!
> Hi @ytx21cn . Thanks for reporting this. I'm able to reproduce the same issue in VS (where I can configure for Linux GCC, using Open Folder, a `CppProperties.json` file,...
@cyente Hi, I am also new to the Qwen3-Coder model. I am wondering if you might also publicize the code for running SWE-bench against the Qwen3-Coder model? Thanks.