mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 13:58:46 +01:00
8cf19d60dc
* check whether platform is 390x if yes->do not import immintrin.h * support s390x big endian * support --bigendian option for s390x 1. verified with baichuan7b-chat with float 16 on s390x 2. verified with baichuan7b-chat 3. verified with chinese-alpaca-2-13b-f16 * update format based on editor-config checker result * Update convert-baichuan-hf-to-gguf.py * 1. check in ggml.c if endianess is not match 2. update GGUF version 3. change get_pack_prefix to property 4. update information log * always use "GGUF" as beginng of GGUF file * Compare "GGUF" with file header char by char 1. Set GGUF_MAGIC to "GGUF" string instead of int value 2. Compare "GGUF" char by char to ensure its byte order 3. Move bytes swap code from convert.py to gguf.py write_tensor_data --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
58 lines
1.8 KiB
C++
58 lines
1.8 KiB
C++
// These tests may take a long time!
|
|
// They are to prove that conversion from double to float of various functions in ggml.c doesn't affect the result.
|
|
// This is done by checking all finite (non-NaN, non-infinite) floats.
|
|
|
|
#undef NDEBUG
|
|
#include <cassert>
|
|
#if !defined(__riscv) && !defined(__s390__)
|
|
#include <immintrin.h>
|
|
#endif
|
|
#include <cmath>
|
|
#include <cstdint>
|
|
#include <cstring>
|
|
|
|
#pragma GCC diagnostic push
|
|
#pragma GCC diagnostic ignored "-Wdouble-promotion"
|
|
|
|
// ggml.c::quantize_row_q4_0_reference
|
|
inline static uint8_t round_orig(float v0) { return ((int8_t) (round(v0))) + 8; }
|
|
|
|
// ggml.c::ggml_silu_f32
|
|
inline static float silu_orig(float x) {
|
|
return x/(1.0 + exp(-x));
|
|
}
|
|
|
|
#pragma GCC diagnostic pop
|
|
|
|
// ggml.c::quantize_row_q4_0_reference
|
|
inline static uint8_t round_float(float v0) { return (int8_t)roundf(v0) + 8; }
|
|
|
|
// ggml.c::ggml_silu_f32
|
|
inline static float silu_float(float x) {
|
|
return x/(1.0f + expf(-x));
|
|
}
|
|
|
|
int main(void) {
|
|
uint32_t x = UINT32_MAX;
|
|
do {
|
|
float f;
|
|
memcpy(&f, &x, sizeof(x));
|
|
assert(!std::isfinite(f) || (round_orig(f) == round_float(f)));
|
|
} while (x--);
|
|
|
|
#ifdef __F16C__
|
|
// GELU and SILU implementations are used with a FP16 lookup table.
|
|
// The original and float-only results are not equal for all inputs after converting to FP16.
|
|
// GELU is an approximation anyway (tanh), not tested here.
|
|
// For SILU, verify that the results are at least the closest floating point numbers, if the FP16 values don't match.
|
|
for (x = 0; x <= UINT16_MAX; x++) {
|
|
float f = _cvtsh_ss(x);
|
|
const float so = silu_orig(f);
|
|
const float sf = silu_float(f);
|
|
assert( (_cvtss_sh(so, 0) == _cvtss_sh(sf, 0))
|
|
|| (nextafterf(so, sf) == sf)
|
|
|| (nextafterf(sf, so) == so));
|
|
}
|
|
#endif
|
|
}
|