Switched remaining tools to streaming output;

Generate contextual prompt datasets as single files per input;
Added Alpaca prompt template;
Generate multiple contextual prompt lengths;
This commit is contained in:
extio-de
2024-11-01 13:43:59 +01:00
parent 2087405c64
commit 7232387134
7 changed files with 178 additions and 76 deletions

View File

@@ -161,13 +161,23 @@ public class Utils {
}
static Path suffixFilename(final Path f, final String... suffixes) {
final String[] parts = f.getFileName().toString().split("[.]");
final StringBuilder sb = new StringBuilder();
for (final String suffix : suffixes) {
sb.append('_');
sb.append(suffix);
if (suffix.charAt(0) != '.') {
sb.append('_');
sb.append(suffix);
}
}
sb.append('.');
return f.getParent().resolve(parts[0] + sb.toString() + parts[1]);
final String[] parts = f.getFileName().toString().split("[.]");
String last;
if (suffixes[suffixes.length - 1].charAt(0) == '.') {
last = suffixes[suffixes.length - 1];
}
else {
last = "." + parts[1];
}
return f.getParent().resolve(parts[0] + sb.toString() + last);
}
}