berkus
/
ANE
mirror of https://github.com/maderix/ANE.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #17 from TastyHeadphones/tastyheadphones/short-dataset-underflow-fix 

Fix token sampling underflow for short token datasets
This commit is contained in:
Manjeet Singh 2026-03-04 17:48:22 +05:30 committed by GitHub
parent 4a6f3e40a9 2b3b7ae5cc
commit 3efa27d7a3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
training/train_large.m
View File

@ -290,6 +290,12 @@ int main(int argc, char *argv[]) {
uint16_t *token_data = (uint16_t*)mmap(NULL, data_len, PROT_READ, MAP_PRIVATE, data_fd, 0); 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; } if (token_data == MAP_FAILED) { printf("mmap failed\n"); return 1; }
size_t n_tokens = data_len / 2; 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); printf("Token data: %zu tokens (%.1f MB)\n", n_tokens, data_len/1e6);
// Gradient buffers shared across layers (reused each step) // Gradient buffers shared across layers (reused each step)