Add research section on DeepSeek-R1T-Chimera

README.md

@@ -13,18 +13,22 @@ short_description: TNG on huggingface
 We solve hard IT problems.
 
 ## Latest Research
-Check out our latest research on "Mixture of Tunable Experts"
+Check out our latest research:
 
-[arXiv: Mixture of Tunable Experts](https://arxiv.org/abs/2502.11096)
-
-[blog: Mixture of Tunable Experts](https://huggingface.co/blog/rbrt/mixture-of-tunable-experts)
+- **DeepSeek-R1T-Chimera**
+  - [Announcement on X](https://x.com/tngtech/status/1916284566127444468)
+  - [Model Card](https://huggingface.co/tngtech/DeepSeek-R1T-Chimera)
+  - More details will follow soon :-)
+- **Mixture of Tunable Experts**
+  - [arXiv: Mixture of Tunable Experts](https://arxiv.org/abs/2502.11096)
+  - [blog: Mixture of Tunable Experts](https://huggingface.co/blog/rbrt/mixture-of-tunable-experts)
 
 ## Blog
 Read our latest blog posts:
 
-[Finetuning olmOCR to be a faithful OCR-Engine](https://huggingface.co/blog/tngtech/finetuning-olmocr-to-be-a-faithful-ocr-engine)
-
-[Efficient Request Queueing – Optimizing LLM Performance](https://huggingface.co/blog/tngtech/llm-performance-request-queueing)
+- [Prefill and Decode for Concurrent Requests - Optimizing LLM Performance ](https://huggingface.co/blog/tngtech/llm-performance-prefill-decode-concurrent-requests)
+- [Finetuning olmOCR to be a faithful OCR-Engine](https://huggingface.co/blog/tngtech/finetuning-olmocr-to-be-a-faithful-ocr-engine)
+- [Efficient Request Queueing – Optimizing LLM Performance](https://huggingface.co/blog/tngtech/llm-performance-request-queueing)
 
 ## Follow us