Add project page link to model card
Browse filesThis PR enhances the model card by adding a direct link to the project page (`https://mukhal.github.io/projects/thinkprm/`) under the "Model Sources" section. This makes it easier for users to find additional information and resources related to the ThinkPRM project.
The existing metadata, paper link, code link, and sample usage are already well-documented and validated by the provided information.
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- reward-model
|
| 5 |
- prm
|
|
@@ -9,8 +11,6 @@ tags:
|
|
| 9 |
- verification
|
| 10 |
- math reasoning
|
| 11 |
- code verification
|
| 12 |
-
license: apache-2.0
|
| 13 |
-
pipeline_tag: text-generation
|
| 14 |
---
|
| 15 |
|
| 16 |
# Model Card for ThinkPRM-7B
|
|
@@ -34,6 +34,7 @@ The model uses a standard language modeling objective, making it interpretable a
|
|
| 34 |
|
| 35 |
- **Repository:** [Github](https://github.com/mukhal/thinkprm)
|
| 36 |
- **Paper:** [Process Reward Models that Think (arXiv:2504.16828)](https://arxiv.org/abs/2504.16828)
|
|
|
|
| 37 |
|
| 38 |
|
| 39 |
### Direct Use
|
|
@@ -126,4 +127,5 @@ Critique: This step is incorrect. Dividing both sides of the equation 2x = 4 by
|
|
| 126 |
Step 2 is \boxed{incorrect}
|
| 127 |
</think>
|
| 128 |
Is the solution correct? No
|
| 129 |
-
"""
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
- reward-model
|
| 7 |
- prm
|
|
|
|
| 11 |
- verification
|
| 12 |
- math reasoning
|
| 13 |
- code verification
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# Model Card for ThinkPRM-7B
|
|
|
|
| 34 |
|
| 35 |
- **Repository:** [Github](https://github.com/mukhal/thinkprm)
|
| 36 |
- **Paper:** [Process Reward Models that Think (arXiv:2504.16828)](https://arxiv.org/abs/2504.16828)
|
| 37 |
+
- **Project Page:** [ThinkPRM Webpage](https://mukhal.github.io/projects/thinkprm/)
|
| 38 |
|
| 39 |
|
| 40 |
### Direct Use
|
|
|
|
| 127 |
Step 2 is \boxed{incorrect}
|
| 128 |
</think>
|
| 129 |
Is the solution correct? No
|
| 130 |
+
"""
|
| 131 |
+
```
|