error: failed to load model 'chatglm3-q8.gguf'
#1
by
telehan
- opened
Log start
main: build = 1839 (5537d9d3)
main: built with Apple clang version 15.0.0 (clang-1500.1.0.2.5) for arm64-apple-darwin23.2.0
main: seed = 1705330824
gguf_init_from_file: invalid magic characters 'ggml'
error loading model: llama_model_loader: failed to load model from chatglm3-q8.gguf
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 'chatglm3-q8.gguf'
main: error: unable to load model
$ shasum -a 256 chatglm3-q8.gguf
d5ab558783322c5c739e6b74c7539a921fa697b4bcc5f1d4c6483b16c2cbc19e chatglm3-q8.gguf
github/llama.cpp$ ./main --version
version: 1839 (5537d9d3)
built with Apple clang version 15.0.0 (clang-1500.1.0.2.5) for arm64-apple-darwin23.2.0