rlhf-feedback-loop 0.6.3 → 0.6.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/bin/cli.js +2 -1
- package/package.json +1 -1
package/bin/cli.js
CHANGED
|
@@ -258,9 +258,10 @@ function summary() {
|
|
|
258
258
|
}
|
|
259
259
|
|
|
260
260
|
function exportDpo() {
|
|
261
|
+
const extraArgs = process.argv.slice(3).join(' ');
|
|
261
262
|
try {
|
|
262
263
|
const output = execSync(
|
|
263
|
-
`node "${path.join(PKG_ROOT, 'scripts', 'export-dpo-pairs.js')}"`,
|
|
264
|
+
`node "${path.join(PKG_ROOT, 'scripts', 'export-dpo-pairs.js')}" --from-local ${extraArgs}`,
|
|
264
265
|
{ encoding: 'utf8', stdio: 'pipe', cwd: CWD }
|
|
265
266
|
);
|
|
266
267
|
process.stdout.write(output);
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "rlhf-feedback-loop",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.4",
|
|
4
4
|
"description": "Make your AI agent learn from mistakes. Capture thumbs up/down feedback, block repeated failures, export DPO training data. Works with ChatGPT, Claude, Codex, Gemini, Amp.",
|
|
5
5
|
"homepage": "https://github.com/IgorGanapolsky/rlhf-feedback-loop#readme",
|
|
6
6
|
"repository": {
|