quyanh / openai_summarize_tldr_sft-dpo
Last scanned: Aug 16, 2025 at 11:44 AM UTC
Versions
Version | Commit message | Commit author | Last scanned | ||
|---|---|---|---|---|---|
| DPO LoRA checkpoint - step 11400 (eval_loss: 1.2601) | quyanh | Aug 16, 2025 | |||
| DPO LoRA checkpoint - step 11300 (eval_loss: 1.2513) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 11200 (eval_loss: 1.2579) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 11100 (eval_loss: 1.2398) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 11000 (eval_loss: 1.2253) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10900 (eval_loss: 1.2207) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10800 (eval_loss: 1.2091) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10700 (eval_loss: 1.1753) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10600 (eval_loss: 1.2102) | quyanh | Aug 16, 2025 | |||
| DPO LoRA checkpoint - step 10500 (eval_loss: 1.2661) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10400 (eval_loss: 1.2887) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10300 (eval_loss: 1.2396) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10200 (eval_loss: 1.2844) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10100 (eval_loss: 1.2777) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 10000 (eval_loss: 1.2282) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 9900 (eval_loss: 1.2397) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 9800 (eval_loss: 1.2434) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 9700 (eval_loss: 1.2482) | quyanh | Aug 16, 2025 | |||
| DPO LoRA checkpoint - step 9600 (eval_loss: 1.2737) | quyanh | Never scanned | |||
| DPO LoRA checkpoint - step 9500 (eval_loss: 1.3414) | quyanh | Never scanned | |||
Protect AI's security scanner detects threats in model files
With Protect AI's Guardian you can scan models for threats before ML developers download them for use, and apply policies based on your risk tolerance.
Found a new threat?
Earn bounties and get recognition for your discoveries by submitting them through Huntr.