glm-4-9b-chat-1m mopdel issue: wrong shape

[0wwafa]

I converted and quantized glm-4-9b-chat-1m in the usual way.
when run with llama I get:

llm_load_print_meta: max token length = 1024
llm_load_tensors: ggml ctx size =    0.14 MiB
llama_model_load: error loading model: check_tensor_dims: tensor 'blk.0.attn_qkv.weight' has wrong shape; expected  4096,  4608, got  4096,  5120,     1,     1
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '/content/glm-4-9b-chat-1m.q5_k.gguf'
main: error: unable to load model

same with all other quants.

I got no errors during conversion nor during quantizations.

[NoobPythoner]

I have the same error.Is there anyone who can fix it ?

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.