LongBench
LongBench copied to clipboard
Any Implementation of new models like Meta-Llama-3.1-8B , Qwen2.5-7B?
I am trying to enable meta-llama-3.1-8B model, not sure if the evaluation results are as expected. Looking forward to the authors' support for more recent base models!
Maybe with the right prompt, base models can also be elegantly evaluated on LongBench v2. Don't hesitate to let us know the results!