Add research section on DeepSeek-R1T-Chimera
Browse files
README.md
CHANGED
|
@@ -13,18 +13,22 @@ short_description: TNG on huggingface
|
|
| 13 |
We solve hard IT problems.
|
| 14 |
|
| 15 |
## Latest Research
|
| 16 |
-
Check out our latest research
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
[
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Blog
|
| 23 |
Read our latest blog posts:
|
| 24 |
|
| 25 |
-
[
|
| 26 |
-
|
| 27 |
-
[Efficient Request Queueing – Optimizing LLM Performance](https://huggingface.co/blog/tngtech/llm-performance-request-queueing)
|
| 28 |
|
| 29 |
## Follow us
|
| 30 |
|
|
|
|
| 13 |
We solve hard IT problems.
|
| 14 |
|
| 15 |
## Latest Research
|
| 16 |
+
Check out our latest research:
|
| 17 |
|
| 18 |
+
- **DeepSeek-R1T-Chimera**
|
| 19 |
+
- [Announcement on X](https://x.com/tngtech/status/1916284566127444468)
|
| 20 |
+
- [Model Card](https://huggingface.co/tngtech/DeepSeek-R1T-Chimera)
|
| 21 |
+
- More details will follow soon :-)
|
| 22 |
+
- **Mixture of Tunable Experts**
|
| 23 |
+
- [arXiv: Mixture of Tunable Experts](https://arxiv.org/abs/2502.11096)
|
| 24 |
+
- [blog: Mixture of Tunable Experts](https://huggingface.co/blog/rbrt/mixture-of-tunable-experts)
|
| 25 |
|
| 26 |
## Blog
|
| 27 |
Read our latest blog posts:
|
| 28 |
|
| 29 |
+
- [Prefill and Decode for Concurrent Requests - Optimizing LLM Performance ](https://huggingface.co/blog/tngtech/llm-performance-prefill-decode-concurrent-requests)
|
| 30 |
+
- [Finetuning olmOCR to be a faithful OCR-Engine](https://huggingface.co/blog/tngtech/finetuning-olmocr-to-be-a-faithful-ocr-engine)
|
| 31 |
+
- [Efficient Request Queueing – Optimizing LLM Performance](https://huggingface.co/blog/tngtech/llm-performance-request-queueing)
|
| 32 |
|
| 33 |
## Follow us
|
| 34 |
|