mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-30 16:07:17 +01:00
f7cab35ef9
CLI to hash GGUF files to detect difference on a per model and per tensor level The hash type we support is: - `--xxh64`: use xhash 64bit hash mode (default) - `--sha1`: use sha1 - `--uuid`: use uuid - `--sha256`: use sha256 While most POSIX systems already have hash checking programs like sha256sum, it is designed to check entire files. This is not ideal for our purpose if we want to check for consistency of the tensor data even if the metadata content of the gguf KV store has been updated. This program is designed to hash a gguf tensor payload on a 'per tensor layer' in addition to a 'entire tensor model' hash. The intent is that the entire tensor layer can be checked first but if there is any detected inconsistencies, then the per tensor hash can be used to narrow down the specific tensor layer that has inconsistencies. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
53 lines
717 B
C
53 lines
717 B
C
#ifndef SHA1_H
|
|
#define SHA1_H
|
|
|
|
/*
|
|
SHA-1 in C
|
|
By Steve Reid <steve@edmweb.com>
|
|
100% Public Domain
|
|
*/
|
|
|
|
#include "stdint.h"
|
|
|
|
#if defined(__cplusplus)
|
|
extern "C" {
|
|
#endif
|
|
|
|
typedef struct
|
|
{
|
|
uint32_t state[5];
|
|
uint32_t count[2];
|
|
unsigned char buffer[64];
|
|
} SHA1_CTX;
|
|
|
|
void SHA1Transform(
|
|
uint32_t state[5],
|
|
const unsigned char buffer[64]
|
|
);
|
|
|
|
void SHA1Init(
|
|
SHA1_CTX * context
|
|
);
|
|
|
|
void SHA1Update(
|
|
SHA1_CTX * context,
|
|
const unsigned char *data,
|
|
uint32_t len
|
|
);
|
|
|
|
void SHA1Final(
|
|
unsigned char digest[20],
|
|
SHA1_CTX * context
|
|
);
|
|
|
|
void SHA1(
|
|
char *hash_out,
|
|
const char *str,
|
|
uint32_t len);
|
|
|
|
#if defined(__cplusplus)
|
|
}
|
|
#endif
|
|
|
|
#endif /* SHA1_H */
|