LLMZoo
LLMZoo copied to clipboard
FreedomIntelligence
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡
In https://github.com/FreedomIntelligence/LLMZoo/tree/main/llmzoo/eval, the readme lacks the 2nd section "How to evaluate?". I am a bit confused by so many scripts and python files. Could you please write a guideline on...
我使用phoenix-inst-chat-7b测试对文档的解读能力，为了控制输出内容，用prompt限制模型在输入内容内生成答案，测试的时候遇到一个bug，大部分问题限制的很好，但是有些问题无论怎么设置都没法限制输出： 先看下输出控制好的： ``` query = '姚明是哪里人？' answer_docs(query) ``` 输出如下：第一行是搜索出来的文档中的5断文字，文字内容和问题毫无关联，模型拒绝回答，这是正确的 Token indices sequence length is longer than the specified maximum sequence length for this model (2441 > 2048). Running this sequence...
cli is running normally   
Metadata
Owner
Metadata
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡