Add library_name and pipeline_tag metadata
Browse filesHi! I'm Niels from the Hugging Face community science team.
This PR improves the model card for KnowRL-DeepSeek-R1-Distill-Qwen-7B by adding relevant metadata:
- `library_name: transformers`: This enables the "Use in Transformers" button and automated code snippets.
- `pipeline_tag: text-generation`: This ensures the model is correctly categorized on the Hub.
- `base_model` and `datasets`: Links the model to its training data and base model for better discoverability.
The content of the model card remains largely the same, maintaining your existing description and usage instructions.
README.md
CHANGED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
<div align="center">
|
|
@@ -7,9 +12,9 @@ license: mit
|
|
| 7 |
<h3 align="center"> Exploring Knowledgeable Reinforcement Learning for Factuality </h3>
|
| 8 |
|
| 9 |
<p align="center">
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
</p>
|
| 14 |
</div>
|
| 15 |
|
|
@@ -67,8 +72,7 @@ huggingface-cli download zjunlp/KnowRL-DeepSeek-R1-Distill-Qwen-7B --local-dir K
|
|
| 67 |
|
| 68 |
The model is trained using Knowledgeable Reinforcement Learning (RL) (specifically GRPO) using data from the `zjunlp/KnowRL-Train-Data`.
|
| 69 |
|
| 70 |
-
For complete details on the training configuration and hyperparameters, please refer to our [GitHub repository](https://github.com/zjunlp/KnowRL
|
| 71 |
-
).
|
| 72 |
|
| 73 |
---
|
| 74 |
|
|
@@ -81,7 +85,4 @@ If you find this model useful in your research, please consider citing our paper
|
|
| 81 |
journal={arXiv preprint arXiv:2506.19807},
|
| 82 |
year={2025}
|
| 83 |
}
|
| 84 |
-
```
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
| 6 |
+
datasets:
|
| 7 |
+
- zjunlp/KnowRL-Train-Data
|
| 8 |
---
|
| 9 |
|
| 10 |
<div align="center">
|
|
|
|
| 12 |
<h3 align="center"> Exploring Knowledgeable Reinforcement Learning for Factuality </h3>
|
| 13 |
|
| 14 |
<p align="center">
|
| 15 |
+
<a href="https://arxiv.org/abs/2506.19807">📄arXiv</a> •
|
| 16 |
+
<a href="https://github.com/zjunlp/KnowRL">💻GitHub Repo</a> •
|
| 17 |
+
<a href="https://huggingface.co/datasets/zjunlp/KnowRL-Train-Data">📖Dataset</a>
|
| 18 |
</p>
|
| 19 |
</div>
|
| 20 |
|
|
|
|
| 72 |
|
| 73 |
The model is trained using Knowledgeable Reinforcement Learning (RL) (specifically GRPO) using data from the `zjunlp/KnowRL-Train-Data`.
|
| 74 |
|
| 75 |
+
For complete details on the training configuration and hyperparameters, please refer to our [GitHub repository](https://github.com/zjunlp/KnowRL).
|
|
|
|
| 76 |
|
| 77 |
---
|
| 78 |
|
|
|
|
| 85 |
journal={arXiv preprint arXiv:2506.19807},
|
| 86 |
year={2025}
|
| 87 |
}
|
| 88 |
+
```
|
|
|
|
|
|
|
|
|