Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# SLAI T-Rex-Pro
|
| 2 |
|
| 3 |
SLAI T-Rex-Pro is the trillion-parameter scale-up of the SLAI T-Rex Operations Research (OR) post-training workflow. Starting from DeepSeek-V4-Pro, it applies full-parameter OR-oriented continued pre-training (CPT) followed by Clean-CoT supervised fine-tuning (SFT) on an optimized Ascend SuperPOD training stack.
|
|
@@ -91,4 +98,4 @@ If you use this model, please cite the technical report:
|
|
| 91 |
archivePrefix= {arXiv},
|
| 92 |
url = {https://arxiv.org/abs/2607.20145}
|
| 93 |
}
|
| 94 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- deepseek-ai/DeepSeek-V4-Flash
|
| 7 |
+
---
|
| 8 |
# SLAI T-Rex-Pro
|
| 9 |
|
| 10 |
SLAI T-Rex-Pro is the trillion-parameter scale-up of the SLAI T-Rex Operations Research (OR) post-training workflow. Starting from DeepSeek-V4-Pro, it applies full-parameter OR-oriented continued pre-training (CPT) followed by Clean-CoT supervised fine-tuning (SFT) on an optimized Ascend SuperPOD training stack.
|
|
|
|
| 98 |
archivePrefix= {arXiv},
|
| 99 |
url = {https://arxiv.org/abs/2607.20145}
|
| 100 |
}
|
| 101 |
+
```
|