Today's llama.cpp-turboquant no loadee - invalid ggml type 45 ?
Hi! Thanks for uploading!
Tried to run with:
$ /pr/Neural/LLM/llama-cpp-turboquant/build/bin/llama-cli -m Qwopus3.5-9B-v3-TQ4_1s.gguf -t 4 -mli --ctx-size 16384 --jinja --fit on -fa on
Loading model... \gguf_init_from_file_ptr: tensor 'blk.2.ffn_gate.weight' has invalid ggml type 45. should be in [0, 41)
gguf_init_from_file_ptr: failed to read tensor info
llama_model_load: error loading model: llama_model_loader: failed to load model from Qwopus3.5-9B-v3-TQ4_1s.gguf
llama_model_load_from_file_impl: failed to load model
llama_params_fit: encountered an error while trying to fit params to free device memory: failed to load model
|gguf_init_from_file_ptr: tensor 'blk.2.ffn_gate.weight' has invalid ggml type 45. should be in [0, 41)
gguf_init_from_file_ptr: failed to read tensor info
/pr/Neural/LLM/llama-cpp-turboquant$ git rev-parse HEAD
e43970099269b5b6da36b8977ad47697602e4e54
Is this an error in the gguf?