Open hzgdeerHo opened 6 months ago
Just know you are not the only one that experiences this.
have a try, turn on flash attention
I encountered the same issue when using LM Studio version 0.2.27. However, when I launched it using text-generation-webui, it worked normally and didn't produce the "GGGG" output even with long context.
TheBloke/deepseek-coder-33B-instruct-GGUF deepseek-coder-33b-instruct.Q6_K.gguf when I use llama cpp python to load the model , the model generates endless "GGGG...." ,But It works normally when the input question less than about 1000-2000 words.