Misc. bug: examples/gguf/gguf.cpp always fails with data check

[nickhuang99]

Name and Version

$ ./llama-cli --version
version: 4959 (53af4db)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu

Operating systems

Linux

Which llama.cpp modules do you know to be affected?

Test code

Command line

$ ./llama-gguf /data/models/./QwQ-32B/QwQ-32B-BF16.gguf r

Problem description & steps to reproduce

$ ./llama-gguf /data/models/./QwQ-32B/QwQ-32B-BF16.gguf r
...
gguf_ex_read_1: reading tensor 0 data
gguf_ex_read_1: tensor[0]: n_dims = 2, ne = (5120, 152064, 1, 1), name = token_embd.weight, data = 0x7f414ef641b0
token_embd.weight data[:10] : 0.016814 -0.043757 0.002697 -0.007346 0.018828 -0.040095 0.018827 -0.010635 0.018583 0.022978

gguf_ex_read_1: tensor[0], data[0]: found 0.016814, expected 100.000000
/home/nick/Downloads/llama.cpp/examples/gguf/gguf.cpp:261: GGML_ASSERT(gguf_ex_read_1(fname, check_data) && "failed to read gguf file") failed
Could not attach to process. If your uid matches the uid of the target
process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf
ptrace: Operation not permitted.
No stack.
The program is not being run.
Aborted (core dumped)

checking source code and I don't understand the logical of data checking below. why if (data[j] != 100 + i) indicates invalid data?

examples/gguf/gguf.cpp:261:

        // check data
        if (check_data) {
            const float * data = (const float *) cur->data;
            for (int j = 0; j < ggml_nelements(cur); ++j) {
                if (data[j] != 100 + i) {
                    fprintf(stderr, "%s: tensor[%d], data[%d]: found %f, expected %f\n", __func__, i, j, data[j], float(100 + i));
                    gguf_free(ctx);
                    return false;
                }
            }
        }

First Bad Commit

No response

Relevant log output