Improve model card: Add library and pipeline tag

README.md

@@ -1,9 +1,10 @@
 ---
 license: llama3
+library_name: transformers
+pipeline_tag: text-generation
 ---
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+# Model Card for LEMMA-LLAMA-3-8B
 
 The LEMMA series models are trained on the [LEMMA Dataset](https://huggingface.co/datasets/panzs19/LEMMA). This dataset uses the training set of MATH and GSM8K to generate error-corrective reasoning trajectories. For each question in these datasets, the student model (LLaMA3-8B) generates self-generated errors, and the teacher model (GPT-4o) deliberately introduces errors based on the error type distribution of the student model. Then, both "Fix & Continue" and "Fresh & Restart" correction strategies are applied to these errors to create error-corrective revision trajectories. After filtering out trajectories with incorrect final answers, we obtain this dataset. Fine-tuning on this dataset achieves up to 13.3% average accuracy improvement for LLaMA3-8B with less than 90k synthesized data. For more details, please refer to our paper [LEMMA: Learning from Errors for MatheMatical Advancement in LLMs](https://arxiv.org/abs/2503.17439).
 
@@ -11,9 +12,9 @@ The LEMMA series models are trained on the [LEMMA Dataset](https://huggingface.c
 
 ### Model Description
 
-- **Finetuned from model [optional]:** [Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
+- **Finetuned from model:** [Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
 
-### Model Sources [optional]
+### Model Sources
 
 - **Repository:** [https://github.com/pzs19/LEMMA/](https://github.com/pzs19/LEMMA/)
 - **Paper:** [https://arxiv.org/abs/2503.17439](https://arxiv.org/abs/2503.17439)
@@ -34,10 +35,10 @@ The LEMMA series models are trained on the [LEMMA Dataset](https://huggingface.c
 
 | Model | Checkpoint | Paper  | GSM8k | MATH  | License |
 | ----- |------| ---- |------|-------| ----- |
-| LEMMA-LLAMA-3-8B | 🤗 <a href="https://huggingface.co/panzs19/LEMMA-LLAMA-3-8B" target="_blank">HF Link</a> |  📃 <a href="" target="_blank">[LEMMA]</a>| **79.2**  |  **38.3**	| <a href="https://www.llama.com/llama3/license/" target="_blank">Llama 3  </a> |
-| LEMMA-LLAMA-3-70B | 🤗 <a href="https://huggingface.co/panzs19/LEMMA-LLAMA-3-70B" target="_blank">HF Link</a> |  📃 <a href="" target="_blank">[LEMMA]</a>| **91.5**  |  **51.8** | <a href="https://www.llama.com/llama3/license/" target="_blank">Llama 3 </a> |
+| LEMMA-LLAMA-3-8B | 🤗 <a href="https://huggingface.co/panzs19/LEMMA-LLAMA-3-8B" target="_blank">HF Link</a> |  📃 <a href="https://huggingface.co/papers/2503.17439" target="_blank">[LEMMA]</a>| **79.2**  |  **38.3**	| <a href="https://www.llama.com/llama3/license/" target="_blank">Llama 3  </a> |
+| LEMMA-LLAMA-3-70B | 🤗 <a href="https://huggingface.co/panzs19/LEMMA-LLAMA-3-70B" target="_blank">HF Link</a> |  📃 <a href="https://huggingface.co/papers/2503.17439" target="_blank">[LEMMA]</a>| **91.5**  |  **51.8** | <a href="https://www.llama.com/llama3/license/" target="_blank">Llama 3 </a> |
 
-## Citation [optional]
+## Citation
 
 Please cite the paper if you refer to our model, code, data or paper from MetaMath.
 
@@ -48,4 +49,4 @@ Please cite the paper if you refer to our model, code, data or paper from MetaMa
   journal={arXiv preprint arXiv:2503.17439},
   year={2025}
 }
-```
+```