Zhouliang Yu

Yes, but if you are using the latest or 2.0+ version, you can just replace `from tensorflow.contrib import layers` to `from tensorflow.keras import layers`

I have the same problem. I tried to upgrade the torch and torchvision version to 1.6.0 and 0.7.0 respectively but it doesn't help

In the beginning, I thought this might be caused because the size of the dataset is too big. Then I tried to use a way smaller dataset. But the issue...

I am using gpt-3.5-turbo, work totally fine when set the agent to be like this: ```python agent = initialize_agent(tools, llm, agent="chat-zero-shot-react-description", verbose=True) ``` after that the agent can choose right...

> I modified the following code and it worked # self.config.n_embd = self.config.hidden_size if hasattr( # self.config, "hidden_size") else self.config.n_embd # todo self.config.n_embd = self.config.vocab_size if hasattr( self.config, "vocab_size") else...

@PaulOrasan Hey, how's the performance after applying null text inversion