Fix README: proper Zen branding

README.md

@@ -1,13 +1,11 @@
-# Zen Coder Training
-
 ---
-title: AutoTrain Advanced
-emoji: 🚀
-colorFrom: blue
-colorTo: green
+title: Zen Coder Training
+emoji: 🔧
+colorFrom: red
+colorTo: gray
 sdk: docker
 pinned: false
-short_description: Create powerful AI models without code
+license: apache-2.0
 hf_oauth: true
 hf_oauth_expiration_minutes: 36000
 hf_oauth_scopes:
@@ -15,26 +13,17 @@ hf_oauth_scopes:
  - write-repos
  - manage-repos
  - inference-api
- - read-billing
 tags:
- - autotrain
+ - zen
+ - training
 ---
 
-# Docs
-
-https://huggingface.co/docs/autotrain
+# Zen Coder Training
 
-# Citation
+Training and fine-tuning infrastructure for Zen Coder models.
 
-@misc{thakur2024autotrainnocodetrainingstateoftheart,
-      title={AutoTrain: No-code training for state-of-the-art models}, 
-      author={Abhishek Thakur},
-      year={2024},
-      eprint={2410.15735},
-      archivePrefix={arXiv},
-      primaryClass={cs.AI},
-      url={https://arxiv.org/abs/2410.15735}, 
-}
+## About
 
+Automated training environment for Zen code-specialized language models, supporting SFT, RLHF, and DPO training pipelines.
 
 **Developed by**: Zen LM Authors