Improve model card: Add abstract and full paper title to link

This PR improves the model card for `Titanesque-OLMo-1B-hf` by:

- Adding the full abstract of the paper, "TPTT: Transforming Pretrained Transformers into Titans", to provide comprehensive context and details about the model's architecture and experimental findings.
- Updating the text of the existing paper link to include the full title `[TPTT: Transforming Pretrained Transformers into Titans]` for better clarity and discoverability.

The metadata, usage example, and existing badge links (including the arXiv link) remain unchanged as they are already accurate and comply with documentation guidelines and disclaimers.

README.md

@@ -1,15 +1,15 @@
 ---
-language: en
-license: apache-2.0
-library_name: transformers
-tags:
-  - tptt
-  - peft
-  - trust_remote_code
-pipeline_tag: text-generation
 base_model: allenai/OLMo-1B-hf
 datasets:
 - yahma/alpaca-cleaned
+language: en
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- tptt
+- peft
+- trust_remote_code
 ---
 
 # Titanesque-OLMo-1B-hf
@@ -34,8 +34,10 @@ datasets:
 
 Titanesque version of `allenai/OLMo-1B-hf` with parallel linearized attention (TPTT 😊) and PEFT.
 
-The architecture was presented in the paper [TPTT](https://huggingface.co/papers/2506.17671).
+The architecture was presented in the paper [TPTT: Transforming Pretrained Transformers into Titans](https://huggingface.co/papers/2506.17671).
 
+## Abstract
+Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose challenges for efficient inference on long contexts and for deployment in resource-limited environments. We present TPTT (Transforming Pretrained Transformers into Titans), a framework designed to augment pretrained Transformers with linearized attention (LiZA) and internal memory gating via Memory as Gate (MaG), applied without full retraining. TPTT supports parameter-efficient fine-tuning (LoRA) and integrates with standard toolkits such as Hugging Face Transformers. We evaluated TPTT on several pretrained models, including Llama-1B, OlMoE-1B-7B, Qwen2.5-1.5B, Gemma3-270m, OpenELM-1.3B, and Mistral-7B, in order to assess applicability across architectures of different scales. Experiments on models with approximately 1 billion parameters, evaluated primarily on the MMLU benchmark, suggest potential improvements in both efficiency and accuracy compared to baseline models. For example, Titans-Llama-1B exhibited up to a 20% relative increase in Exact Match scores in one-shot evaluation. An additional finding is that it is possible to convert a quadratic-attention model into a purely linear-attention model using the DeltaProduct mechanism. All training runs were carried out with modest computational resources. These preliminary findings indicate that TPTT may help adapt pretrained LLMs for long-context tasks with limited overhead. Further studies on larger models and a broader set of benchmarks will be necessary to evaluate the generality and robustness of the framework. Code is available at this https URL . Python package at this https URL .
 
 ## Model list
 
@@ -45,7 +47,7 @@ Classic model parameter with LiZA injection :
 |-------------------------------|----------------------|------------|------------|----------------|---------------|------|-------------------------------------------------------|
 | delta_rule  | 8192 (default)       | 0.5        | False      | 64             | False         | Yes  | Parallel linearized attention with delta_rule operator|
 | delta_rule_gelu | 8192 (default) | 0.5        | False      | 64             | False         | Yes  | Non-linear operator with gelu activation              |
-| delta_product    | 8192 (default) | 0.5        | False      | 64             | False         | Yes  | Second order operator with derivative trick              |
+| delta_product    | 8192 (default) | 0.5        | False         | 64             | False         | Yes  | Second order operator with derivative trick              |
 | delta_product_r  | 8192 (default) | 0.5        | False      | 64             | False         | Yes  | Second order operator with rotative trick             |
 | delta_product_c  | 8192 (default) | 0.5        | False      | 64             | False         | Yes  | Second order operator with combined trick             |
 
@@ -73,5 +75,4 @@ print(tokenizer.decode(outputs, skip_special_tokens=True))
 
 If you use TPTT in your academic work, please cite [Furfaro](https://huggingface.co/ffurfaro). For questions or support, please open an issue on the [GitHub repository](https://github.com/fabienfrfr/tptt) or contact the maintainer.
 
-
 ---