THUDM/LongBench Issues
Chinese Examples in MultiFieldQA-en
Updated 1Table reproduce
ClosedLlama2-7B-chat-4k测试出来结果不一样
Closed 3求问 Spearman correlation 是怎么计算的
Updated 1CUDA error??????
Closedhow to apply to baichuan?
Closed 1Kimi-Chat 测试
Closed 1如何评测GPT-3.5或GPT-4
Closed 3Any Implementation of Mistral-7B?
Updated 1测试13b，比如百川，1*A100（80G）会OOM
UpdatedKeyError: 'retrieved'
Closed 3OOM
Closed 3单卡A100无法推理
Closed 3长度外推的三种方式得到的answer竟一模一样？
Closed关于被测试的模型
Closed 2关于评测的合理性
Closed 2classification_score计算得分代码有误
Closed 1pred.py中的typo
Closed 1关于TREC数据集中的typo
Updated 1llama2 chat's template
Closed 5LongBench-E和LongBench有什么区别？
Closed 2Error with multi-gpus
Closed超长文本的推理OOM
Closed 11Questions on dataset answers.
Closed 3LongbenchE & Longbench
Closed 1Max length not guarenteed
Closed 2Cannot load LongBench-E
Closed 1add support for other models
Closed 3关于截断长度的公平性问题
Closed 2why use greedy decoding ?
Closed 1评测是否能用于Base模型?
Closed 1About prompt
Closed 1requreiments.txt
Closed 1