Dr. Cat Lu

The function of resuming offline runs is very useful. Many guys are using commercial GPU servers to train their models, the GPU server often has the longest running time limit...

Hi @Blaizzy , Thanks for your quick response. For the students in University, in the lab, the GPU server always lacks, because training a neural network is time-consuming work, and...

Hi @Blaizzy Hope to hear from you soon. By now, no more questions. Anyway, thank you again.

The offline resume is useful for offline logging. Using online mode will decrease the long-time training speed. For using cloud GPU services, such as Kaggle, and Google's colab, the training...

Test Case : for wandb, version 0.13.9 id = '20230121' wandb.init( id=id, resume="auto", mode="offline", project="test-2023", config={"first_run": True} ) Msg ： WARNING `resume` will be ignored since W&B syncing is set...

yep, this error is related to LSTM output.

[CN] 采用 langchain的样例，目前的嵌入模型被下载后是放在ModelScope的cache目录中，虽然不会重复下载，但迁移起来还是有点麻烦，但通常可以在环境变量中设置cache目录和下载目录进行管理，所以下载和管理本地嵌入模型的问题不大，特别是llamaindex的例子，在Settgins里面可以用 local进行修饰，明确调用本地模型。 现在遇到的问题是，对于 MemoryWithRetrievalKnowledge 系列的例子，这个嵌入模型的前置Agent使用的LLM和embedding嵌入之间有依赖关系。qwen-max + damo/nlp_gte_sentence-embedding_chinese-base， OK； qwen-max + Xorbits/bge-large-zh-v1.5， error， siliconflow的qwen-7b+damo/nlp_gte_sentence-embedding_chinese-base， error。我猜测换ollama 经过简单测试可以发现 MemoryWithRetrievalKnowledge 这个工具内耦合的比较重。 相比 llmaindex_rag的例子对这种组合测试就可以轻松过关。 如果大师们有空帮忙看看应该从那个角度入手去解决问题。 [EN] Using the example of langchain, the current...

Having several intelligent agents from AgentScope and other third-party agents communicating with each other is an exciting idea. Before continuing the discussion, we need to clarify a few things. What...

Roger that, Thanks.