Improve model card: Add pipeline tag, library name, and prominent links

This PR enhances the model card by:
* Adding the `pipeline_tag: text-generation` and `library_name: transformers` metadata, ensuring proper discoverability on the Hugging Face Hub and enabling the "How to use" widget.
* Including direct, prominent links to the paper's Hugging Face page, the project page, and the GitHub repository at the top of the model card for easier access to relevant resources.
* Correcting an existing inline link that incorrectly labeled the project page as the paper.

README.md

@@ -1,6 +1,14 @@
 ---
+base_model:
+- EleutherAI/deep-ignorance-pretraining-stage-unfiltered
+datasets:
+- EleutherAI/deep-ignorance-pretraining-mix
+- EleutherAI/deep-ignorance-annealing-mix
 language:
 - en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 tags:
 - pytorch
 - causal-lm
@@ -25,19 +33,15 @@ tags:
 - safety-research
 - model-diffing
 - training-dynamics
-license: apache-2.0
-datasets:
-- EleutherAI/deep-ignorance-pretraining-mix
-- EleutherAI/deep-ignorance-annealing-mix
-base_model:
-- EleutherAI/deep-ignorance-pretraining-stage-unfiltered
 ---
 
 # Deep Ignorance Model Suite
 
+[📄 Paper](https://huggingface.co/papers/2508.06601) | [🌐 Project Page](https://deepignorance.ai/) | [💻 GitHub Repository](https://github.com/EleutherAI/deep-ignorance)
+
 We explore an intuitive yet understudied question: Can we prevent LLMs from learning unsafe technical capabilities (such as CBRN) by filtering out enough of the relevant pretraining data before we begin training a model? Research into this question resulted in the **Deep Ignorance Suite**. In our experimental setup, we find that filtering pretraining data prevents undesirable knowledge, doesn't sacrifice general performance, and results in models that are resistant to tampering.
 
-Deep Ignorance is a collection of 6.9B models developed to facilitate research into pretraining, interpretability, training data, and unlearning [(see paper)](https://deepignorance.ai). It contains 18 models composing of a baseline model trained on unfiltered data, and 17 models trained on filtered datasets or with other safety interventions being applied. Pretraining stage models have 101 checkpoints and annealing stage have 11.
+Deep Ignorance is a collection of 6.9B models developed to facilitate research into pretraining, interpretability, training data, and unlearning ([see project page](https://deepignorance.ai)). It contains 18 models composing of a baseline model trained on unfiltered data, and 17 models trained on filtered datasets or with other safety interventions being applied. Pretraining stage models have 101 checkpoints and annealing stage have 11.
 
 > **Support:**
 > The #release-discussion channel in the [EleutherAI Discord](https://discord.gg/eleutherai) is the best place to ask questions. Questions asked in other channels are less likely to be answered. The community section on HuggingFace is less actively monitored. Tag Kyle O'Brien in the EleutherAI Discord for faster response times.
@@ -51,9 +55,6 @@ Our research and model suite open up multiple avenues for future work. For insta
 
 We are also excited for the community to stress test data filtering to determine whether there are some situations where it is less tamper-resistant than our experiments suggest! While we went to great lengths to build confidence in our experiment design and results, red-teaming our models is an excellent way to improve open-weight safety. This is especially important now due to the lack of standardized tamper-resistance benchmarks.
 
-
-
-
 ## Uses and Limitations
 
 ### Quickstart