최창윤
It is not operated in my environ because of the version of 'keras.layers'. My version is keras==1.2.1 and tensorflow==1.15.4 Also, h5py must be 2.xx version when load the weight files.
1. Correct the error to use .reshape for model learning in the latest version of pytorch. 2. Added the function to learn using certain nodes only. 3. Added the function...
If you make custom prompt work as per #486, you should write the output parser. Additionally, it seems that need to list all the items available as config for prompts...
Fixed an issue where the LLM model and custom prompts could not distinguish between main and other tasks.
Hello. I understand that the way to pass context to chat in API format is "role":"context". What if I want to put a specific value in the Context variable on...
Hello. I have a question about managing conversation history. I want to save the history and state of an ongoing conversation, recall an existing conversation based on a key value,...
Hello. Thank you for providing a useful chat framework. I am creating a TOD system and want to extract slot-values from the user's utterances, store them in the context, and...
When following the tutorial from the link below: https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Conceptual_Guide/Part_1-model_deployment/README.html#launching-the-server an error occurs in the config.pbtxt for text_recognition: "failed to load 'text_recognition' version 1: Invalid argument: unexpected inference output '308', allowed...