raygogogo
raygogogo
> ``` > import os, pdb > from langchain.embeddings.openai import OpenAIEmbeddings > from langchain.text_splitter import CharacterTextSplitter, TokenTextSplitter > from langchain.vectorstores import Milvus > from langchain.document_loaders import TextLoader > from langchain.embeddings...
Hi this feature can be merge now?
> VectorDBQAWithSourcesChain could you provide more information about your program, especially regarding AzureLLM and the PromptTemplate. i think the KeyError 'source' is because your prompt template missing the key.
> 19 Hi what's your input for llm and how do you build your chain, could you offer more information
> 我就说不可能把ok的模型放出来哈,只可惜为了测试这个花的银子买硬件...... 哈哈哈哈 根本 finetune 不起,但是 base 版本的效果这么扯,难道全靠 instruction?
> 对啊,部署测了下效果相当差,不入6B版本,尽然在很多榜单上效果都不错,严重怀疑给的模型不是测试的版本 我看有个哥们还跑了测试 [#94](https://github.com/THUDM/GLM-130B/issues/94)
> > 我也遇见了,有人解决了么 > > 我解决了 能分享一下量化后的程序吗