Update README.md

README.md

@@ -27,9 +27,9 @@ tags:
   <a href="https://discord.gg/P2yYH95N" target="_blank" style="margin: 2px;">
     <img alt="Discord" src="https://img.shields.io/badge/Discord-Small%20Doges-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
   </a>
-  <a href="https://arxiv.org/abs/2412.11834" target="_blank" style="margin: 2px;">
+  <!-- <a href="https://arxiv.org/abs/2412.11834" target="_blank" style="margin: 2px;">
     <img alt="arXiv" src="https://img.shields.io/static/v1?label=arXiv&message=2412.11834&color=B31B1B&logo=arXiv" style="display: inline-block; vertical-align: middle;"/>
-  </a>
+  </a> -->
   <a href="https://github.com/SmallDoges/small-doge" target="_blank" style="margin: 2px;">
     <img alt="GitHub" src="https://img.shields.io/badge/GitHub-SmallDoge-181717?logo=github" style="display: inline-block; vertical-align: middle;"/>
   </a>
@@ -85,19 +85,31 @@ outputs = model.generate(
 
 We build the Doge-Instruct by first SFT on [SmolTalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) and then DPO on [UltraFeedback Binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized).
 
-> TODO: The larger model is under training and will be uploaded soon.
-
 **SFT**:
 | Model | Training Data | Epochs | Content Length | LR | Batch Size | Precision |
 |---|---|---|---|---|---|---|
-| [Doge-20M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-20M-Instruct-SFT) | [HuggingFaceTB/smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 8e-4 | 0.25M | bfloat16 |
-| [Doge-60M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-60M-Instruct-SFT) | [HuggingFaceTB/smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 6e-4 | 0.25M | bfloat16 |
+| [Doge-20M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-20M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 8e-4 | 0.25M | bfloat16 |
+| [Doge-60M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-60M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 6e-4 | 0.25M | bfloat16 |
+| [Doge-160M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-160M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 4e-4 | 0.25M | bfloat16 |
+| [Doge-320M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-320M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 2e-4 | 0.25M | bfloat16 |
 
 **DPO**:
 | Model | Training Data | Epochs | Content Length | LR | Batch Size | Precision |
 |---|---|---|---|---|---|---|
-| [Doge-20M-Instruct](https://huggingface.co/SmallDoge/Doge-20M-Instruct) | [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 8e-5 | 0.125M | bfloat16 |
-| [Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) | [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 6e-5 | 0.125M | bfloat16 |
+| [Doge-20M-Instruct](https://huggingface.co/SmallDoge/Doge-20M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 8e-5 | 0.125M | bfloat16 |
+| [Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 6e-5 | 0.125M | bfloat16 |
+| [Doge-160M-Instruct](https://huggingface.co/SmallDoge/Doge-160M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 4e-5 | 0.125M | bfloat16 |
+| [Doge-320M-Instruct](https://huggingface.co/SmallDoge/Doge-320M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 2e-5 | 0.125M | bfloat16 |
+
+
+**Evaluation**:
+
+| Model | IFEval (Prompt Strict Acc) | MMLU | BBH | ARC | PIQA | HellaSwag | tokens / s on i7-11 CPU |
+|---|---|---|---|---|---|---|---|
+| [Doge-20M-Instruct](https://huggingface.co/SmallDoge/Doge-20M-Instruct) | 7.3 | 26.3 | 18.3 | 29.2 | 57.8 | 27.8 | 142 |
+| [Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) | 7.4 | 27.5 | 27.7 | 37.5 | 61.4 | 32.1 | 62 |
+| [Doge-160M-Instruct](https://huggingface.co/SmallDoge/Doge-160M-Instruct) | 16.8 | 29.7 | 29.1 | 42.8 | 64.1 | 37.1 | 28 |
+| [Doge-320M-Instruct](https://huggingface.co/SmallDoge/Doge-320M-Instruct) | 28.5 | 30.3 | 31.9 | 51.7 | 71.0 | 50.6 | 16 |
 
 
 **Procedure**:
@@ -118,13 +130,11 @@ We build the Doge-Instruct by first SFT on [SmolTalk](https://huggingface.co/dat
 ## Citation
 
 ```bibtex
-@misc{shi2024wonderfulmatrices,
-      title={Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture}, 
-      author={Jingze Shi and Bingheng Wu},
-      year={2024},
-      eprint={2412.11834},
-      archivePrefix={arXiv},
-      primaryClass={cs.LG},
-      url={https://arxiv.org/abs/2412.11834}, 
+@misc{smalldoges,
+  title={SmallDoges: A Family of Dynamic UltraFast Small Language Models}, 
+  author={Jingze, Shi and Yifan, Wu and Bingheng, Wu and Yuyu, Luo},
+  year={2025},
+  month={March},
+  url={https://github.com/SmallDoges/small-doge}
 }
 ```