Improve model card: Add paper link, pipeline_tag, and library_name
Browse filesThis PR improves the model card for TrueGL_Granite by:
- Linking directly to the paper [TrueGL: A Truthful, Reliable, and Unified Engine for Grounded Learning in Full-Stack Search](https://huggingface.co/papers/2506.12072).
- Adding the `pipeline_tag: text-generation` to ensure the model is discoverable under relevant tasks, reflecting its capability to return textual explanations alongside reliability scores.
- Adding `library_name: transformers` as the model's `config.json` and `tokenizer_config.json` indicate compatibility, enabling the automated code snippet for users.
README.md
CHANGED
|
@@ -1,11 +1,19 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
-
language:
|
| 4 |
-
- en
|
| 5 |
base_model:
|
| 6 |
- ibm-granite/granite-3.0-1b-a400m-base
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |

|
| 10 |
|
| 11 |
We are developing a search engine that introduces a novel AI-driven truth and reliability scoring system, assigning each search result a truth parameter on a scale of 0 (lie) to 1 (absolute truth).
|
|
@@ -17,5 +25,4 @@ Our GitHub repository (with the fine-tuning and inference code) is publicly avai
|
|
| 17 |
Note that the project is created for educational and research purposes only and is not intended for commercial use. The data used for training and fine-tuning the AI models is either collected from open-sources or AI-generated and is not collected or used in any way that violates privacy or ethical guidelines.
|
| 18 |
|
| 19 |
We are always looking for the motivated collaborators to join us in this exciting project. If you are interested in contributing to the development of this search engine, please feel free to reach out to us!
|
| 20 |
-
!
|
| 21 |
-
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- ibm-granite/granite-3.0-1b-a400m-base
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
license: mit
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: transformers
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# TrueGL_Granite
|
| 12 |
+
|
| 13 |
+
This model is a fine-tuned version of IBM's Granite-1B, presented in the paper [TrueGL: A Truthful, Reliable, and Unified Engine for Grounded Learning in Full-Stack Search](https://huggingface.co/papers/2506.12072).
|
| 14 |
+
|
| 15 |
+
The model is designed to return a textual explanation alongside a reliability score, making trustworthy search results more accessible.
|
| 16 |
+
|
| 17 |

|
| 18 |
|
| 19 |
We are developing a search engine that introduces a novel AI-driven truth and reliability scoring system, assigning each search result a truth parameter on a scale of 0 (lie) to 1 (absolute truth).
|
|
|
|
| 25 |
Note that the project is created for educational and research purposes only and is not intended for commercial use. The data used for training and fine-tuning the AI models is either collected from open-sources or AI-generated and is not collected or used in any way that violates privacy or ethical guidelines.
|
| 26 |
|
| 27 |
We are always looking for the motivated collaborators to join us in this exciting project. If you are interested in contributing to the development of this search engine, please feel free to reach out to us!
|
| 28 |
+
!
|
|
|