Why has only file 1 of BF16 been updated?
#13
by erazortt - opened
Only file gemma-4-31B-it-BF16-00001-of-00002.gguf has been updated. The model cannot be quantized like that. I am getting this error furing quantization:
llama_model_quantize: failed to quantize: tensor 'blk.59.ffn_gate.weight' data is not within the file bounds, model is corrupted or incomplete