failed to read tensor info
Sorry could you elaborate?
you know, when i use this model by google colab in the page of hf, i follow the previous code written by hf, it always fail. I updated the version of llama.cpp ,but it also failed. and below is the fail.
gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' has invalid ggml type 39 (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 /root/.cache/huggingface/hub/models--unsloth--gpt-oss-20b-GGUF/snapshots/ff0f965518cc8b299d10c1318d42c6e15689f11e/./gpt-oss-20b-F16.gguf
llama_model_load_from_file_impl: failed to load model
Good day, I encountered a similar problem, but with the version gpt-oss-20b-Q5KM, and I couldn't fix it.
I am getting the same error as well
same error on Q4