TheBloke
/

OpenAssistant-SFT-7-Llama-30B-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Resources

View closed (10)

What pre-prompt and prompt structure to use? + sometimes the model replies only with "\u200b" (zero-width space character)

#12 opened almost 2 years ago by

HuggingFaceH4/starchat-alpha CPP CPU

#8 opened almost 2 years ago by

Exception on downloading the model

#7 opened almost 2 years ago by

RuntimeError: shape '[-1, 1024, 6656]' is invalid for input of size 44302336

#6 opened almost 2 years ago by

How should I call this model to implement the Q&A

#1 opened almost 2 years ago by