tensor 'blk.25.ffn_down.weight' has invalid ggml type 42 (NONE)

[evaninf]

Name and Version

version: 4726 (6dde1782) built with cc (GCC) 14.2.1 20250110 (Red Hat 14.2.1-7) for x86_64-redhat-linux

Operating systems

Linux

GGML backends

CPU

Hardware

AMD Ryzen 7 4800H with Radeon Graphics

Models

Llama3-8B-1.58-100B-tokens-GGUF Falcon3-10B-Instruct-1.58bit-GGUF

Problem description & steps to reproduce

Trying to use any of the models results in the error.

First Bad Commit

No response

Relevant log output

build: 4726 (6dde1782) with cc (GCC) 14.2.1 20250110 (Red Hat 14.2.1-7) for x86_64-redhat-linux
main: llama backend init
main: load the model and apply lora adapter, if any
gguf_init_from_file_impl: tensor 'blk.25.ffn_down.weight' has invalid ggml type 42 (NONE)
gguf_init_from_file_impl: failed to read tensor info
llama_model_load: error loading model: llama_model_loader: failed to load model from /mnt/model/Llama3-8B-1.58-100B-tokens-q2b1.gguf

llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '/mnt/model/Llama3-8B-1.58-100B-tokens-q2b1.gguf'
main: error: unable to load model