CoolFace
Modelpublic

Moeblack/longzu-dpo-lora

sourceHugging Faceupdated 1mo agoView on Hugging Face
0likes
13 commits on main
259cf161mo ago

Training in progress, step 44

Moeblack
5dc6d7b1mo ago

full ckpt checkpoint-44

Moeblack
327d0f51mo ago

cleanup tokentest

Moeblack
e6831441mo ago

tokentest

Moeblack
2de49bf1mo ago

full ckpt checkpoint-60 (含 optimizer.pt/scheduler.pt)

Moeblack
6da63fd1mo ago

Training in progress, step 60

Moeblack
274f4481mo ago

full ckpt checkpoint-1 (含 optimizer.pt/scheduler.pt)

Moeblack
d877fa21mo ago

Training in progress, step 1

Moeblack
ef3daa01mo ago

full ckpt checkpoint-1 (含 optimizer.pt/scheduler.pt)

Moeblack
86b22441mo ago

Training in progress, step 1

Moeblack
b40edb01mo ago

dpo v1 final

Moeblack
30d12e31mo ago

Training in progress, step 1

Moeblack
e3191541mo ago

initial commit

Moeblack