LuoKaiGSW

sometimes gold_patch cannot pass the test

6

This is a very challenging benchmark, I have learned a lot from it. Thank you for the effort you have put into this. I tested using the swe-llama13b you provided...

The output has garbled text issues

1

When I use llama7b after sft on sglang, I find that the output has garbled text. However, the output is normal when not using sglang. What could be the reason...

about requirements

2

When I attempted to run the command pip install "sglang[all]", I encountered an error: "The NVIDIA driver on your system is too old (found version 11080)." Could you provide information...

Regarding the execution of SGLang programs, the paper mentions that it can be done through an interpreter or a compiler. Additionally, it is described as follows: "Alternatively, a limited set...

通用数据如何筛选

7

想问一下，通用数据ShareGPT_Vicuna_unfiltered有9w条，你们是如何筛选到5w条的？能提供一下脚本吗

How can I get the mapping relationship between byte values and Unicode characters of the fast tokenizer?

5

I have a model that uses BloomTokenizerFast, which does not have properties like byte_decoder and sp_model, so I can't figure out how it implements the mapping between byte values and...

Abnormal output appears when decoding with guidance

10

I obtained a model for tool invocation through SFT. When I use guidance for decoding, the output result is garbled. However, if I output directly, the result is correct. One...

Thank you for your work! Currently, most of the community is using Lean4 for data synthesis. I would like to ask if there is any quick way for this project...