Weichen Li

Results 1 comments of Weichen Li

I have the similar problem, when I use code below to load llama model: `llm = Llama(model_path="./models/llama-2-7b-chat.Q4_K_M.gguf", verbose=False, n_gpu_layers=30)` Then an exception will be throwed: > Exception ignored in: Traceback...