This commit is contained in:
TastyHeadphones 2026-03-04 22:22:00 +09:00 committed by GitHub
commit 2bd5e7e93c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 18 additions and 6 deletions

View File

@ -284,6 +284,12 @@ int main(int argc, char *argv[]) {
uint16_t *token_data = (uint16_t*)mmap(NULL, data_len, PROT_READ, MAP_PRIVATE, data_fd, 0);
if (token_data == MAP_FAILED) { printf("mmap failed\n"); return 1; }
size_t n_tokens = data_len / 2;
if (n_tokens <= (size_t)(SEQ + 1)) {
printf("Token data too short: need at least %d tokens, got %zu\n", SEQ + 2, n_tokens);
munmap(token_data, data_len);
close(data_fd);
return 1;
}
printf("Token data: %zu tokens (%.1f MB)\n", n_tokens, data_len/1e6);
// Gradient buffers

View File

@ -335,12 +335,18 @@ int main(int argc, char *argv[]) {
// mmap token data
int data_fd = open(DATA_PATH, O_RDONLY);
if (data_fd < 0) { printf("Cannot open %s\n", DATA_PATH); return 1; }
struct stat st; fstat(data_fd, &st);
size_t data_len = st.st_size;
uint16_t *token_data = (uint16_t*)mmap(NULL, data_len, PROT_READ, MAP_PRIVATE, data_fd, 0);
if (token_data == MAP_FAILED) { printf("mmap failed\n"); return 1; }
size_t n_tokens = data_len / 2;
printf("Token data: %zu tokens (%.1f MB)\n", n_tokens, data_len/1e6);
struct stat st; fstat(data_fd, &st);
size_t data_len = st.st_size;
uint16_t *token_data = (uint16_t*)mmap(NULL, data_len, PROT_READ, MAP_PRIVATE, data_fd, 0);
if (token_data == MAP_FAILED) { printf("mmap failed\n"); return 1; }
size_t n_tokens = data_len / 2;
if (n_tokens <= (size_t)(SEQ + 1)) {
printf("Token data too short: need at least %d tokens, got %zu\n", SEQ + 2, n_tokens);
munmap(token_data, data_len);
close(data_fd);
return 1;
}
printf("Token data: %zu tokens (%.1f MB)\n", n_tokens, data_len/1e6);
// Vocab compaction: map 32K sparse vocab ~9K compact
VocabMap vm = vocab_map_build(token_data, n_tokens, VOCAB);