tencent/IFMTBench download history
tencent/IFMTBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 211 times (70 in the last 7 days), and 1,412 times in total. It ranks #86,072 among datasets by monthly downloads.
Translation Instruction Following Benchmark A benchmark for evaluating how well LLMs follow complex instructions during translation tasks. The benchmark covers 6 constraint types across multiple languages, including single-constraint and multi-constraint scenarios. Constra
Open tencent/IFMTBench on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.