schihei/llama2.c
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

small stylistic fixes and adjustments, fix bug in Makefile, and change the timing code to skip the first (slow) iteration

Browse Source
This commit is contained in:
Andrej Karpathy
2023-07-27 22:42:08 +00:00
parent 0e1b0d4c93
commit 25b50ee0e2
2 changed files with 14 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Makefile
+1 -1
View File
@@ -42,7 +42,7 @@ rungnu:
$(CC) -Ofast -std=gnu11 -o run run.c -lm $(CC) -Ofast -std=gnu11 -o run run.c -lm
.PHONY: runompgnu .PHONY: runompgnu
rungnu: runompgnu:
$(CC) -Ofast -fopenmp -std=gnu11 run.c -lm -o run $(CC) -Ofast -fopenmp -std=gnu11 run.c -lm -o run
.PHONY: clean .PHONY: clean
run.c
+10 -14
View File
@@ -193,6 +193,7 @@ void softmax(float* x, int size) {
void matmul(float* xout, float* x, float* w, int n, int d) { void matmul(float* xout, float* x, float* w, int n, int d) {
// W (d,n) @ x (n,) -> xout (d,) // W (d,n) @ x (n,) -> xout (d,)
// by far the most amount of time is spent inside this little function
int i; int i;
#pragma omp parallel for private(i) #pragma omp parallel for private(i)
for (i = 0; i < d; i++) { for (i = 0; i < d; i++) {
@@ -398,15 +399,12 @@ int main(int argc, char *argv[]) {
// read in the model.bin file // read in the model.bin file
Config config; Config config;
TransformerWeights weights; TransformerWeights weights;
int fd = 0; int fd = 0; // file descriptor for memory mapping
float* data = NULL; float* data = NULL; // memory mapped data pointer
long file_size; long file_size; // size of the checkpoint file in bytes
{ {
FILE *file = fopen(checkpoint, "rb"); FILE *file = fopen(checkpoint, "rb");
if (!file) { if (!file) { printf("Couldn't open file %s\n", checkpoint); return 1; }
printf("Unable to open the checkpoint file %s!\n", checkpoint);
return 1;
}
// read in the config header // read in the config header
if(fread(&config, sizeof(Config), 1, file) != 1) { return 1; } if(fread(&config, sizeof(Config), 1, file) != 1) { return 1; }
// negative vocab size is hacky way of signaling unshared weights. bit yikes. // negative vocab size is hacky way of signaling unshared weights. bit yikes.
@@ -431,11 +429,7 @@ int main(int argc, char *argv[]) {
char** vocab = (char**)malloc(config.vocab_size * sizeof(char*)); char** vocab = (char**)malloc(config.vocab_size * sizeof(char*));
{ {
FILE *file = fopen("tokenizer.bin", "rb"); FILE *file = fopen("tokenizer.bin", "rb");
if (!file) { if (!file) { printf("Couldn't load tokenizer.bin\n"); return 1; }
printf("Unable to open the tokenizer file tokenizer.bin! Run "
"python tokenizer.py to convert tokenizer.model -> tokenizer.bin\n");
return 1;
}
int len; int len;
for (int i = 0; i < config.vocab_size; i++) { for (int i = 0; i < config.vocab_size; i++) {
if(fread(&len, sizeof(int), 1, file) != 1) { return 1; } if(fread(&len, sizeof(int), 1, file) != 1) { return 1; }
@@ -451,7 +445,7 @@ int main(int argc, char *argv[]) {
malloc_run_state(&state, &config); malloc_run_state(&state, &config);
// the current position we are in // the current position we are in
long start = time_in_ms(); long start = 0; // used to time our code, only initialized after first iteration
int next; int next;
int token = 1; // 1 = BOS token in Llama-2 sentencepiece int token = 1; // 1 = BOS token in Llama-2 sentencepiece
int pos = 0; int pos = 0;
@@ -479,11 +473,13 @@ int main(int argc, char *argv[]) {
// advance forward // advance forward
token = next; token = next;
pos++; pos++;
// init our timer here because the first iteration is slow due to memmap
if (start == 0) { start = time_in_ms(); }
} }
// report achieved tok/s // report achieved tok/s
long end = time_in_ms(); long end = time_in_ms();
printf("\nachieved tok/s: %f\n", steps / (double)(end-start)*1000); printf("\nachieved tok/s: %f\n", (steps-1) / (double)(end-start)*1000);
// memory and file handles cleanup // memory and file handles cleanup
free_run_state(&state); free_run_state(&state);