wzx111
/

Qwen3-1.7B-Open-R1-ADPO

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

wzx111 commited on Nov 23, 2025

Commit

22b25fa

·

verified ·

1 Parent(s): af913b5

Training in progress, epoch 1

Files changed (3) hide show

README.md +1 -1
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/kingpalace/open-r1-ADPO/runs/tgb2dnwx)
 This model was trained with ADPO, a method introduced in [Anchored Direct Preference Optimization](https://huggingface.co/papers/2510.18913).

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/kingpalace/open-r1-ADPO/runs/zyvkql11)
 This model was trained with ADPO, a method introduced in [Anchored Direct Preference Optimization](https://huggingface.co/papers/2510.18913).

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8a6c4e463ee72a328784138bcd79259c65d2a9d90744605c9550f96ff8bbd6
 size 4063515640

 version https://git-lfs.github.com/spec/v1
+oid sha256:d553d0a8ee94618a67269695ed88a14ea2b97f0e07e146d6eee1e06520ead2ff
 size 4063515640

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3f24ed5aca214acdef132699606077dbd3bb580d61282ad2ac4a228fe4c0cc
 size 9809

 version https://git-lfs.github.com/spec/v1
+oid sha256:10bfd2fa059bf75d5796acc51aa855b52609b29b4271dc1647bd1121652759c0
 size 9809