Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,37 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
base_model:
|
| 5 |
+
- deepseek-ai/DeepSeek-V3-0324
|
| 6 |
+
- deepseek-ai/DeepSeek-R1
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
---
|
| 9 |
+
# DeepSeek-R1T-Chimera
|
| 10 |
+
|
| 11 |
+
<div align="center">
|
| 12 |
+
<img src="https://www.tngtech.com/_astro/TNG_Logo.URm66zYr_Z2aCrIU.svg"
|
| 13 |
+
alt="TNG Logo"
|
| 14 |
+
width="400"
|
| 15 |
+
style="display: inline-block; vertical-align: middle;"/>
|
| 16 |
+
</div>
|
| 17 |
+
<br>
|
| 18 |
+
<div align="center">
|
| 19 |
+
<a href="LICENSE" style="margin: 2px;">
|
| 20 |
+
<img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
|
| 21 |
+
</a>
|
| 22 |
+
</div>
|
| 23 |
+
|
| 24 |
+
**Model merge of DeepSeek-R1 and DeepSeek-V3 (0324)**
|
| 25 |
+
|
| 26 |
+
An open weights model combining the intelligence of R1 with the token efficiency of V3.
|
| 27 |
+
|
| 28 |
+
## Model Details
|
| 29 |
+
|
| 30 |
+
- **Architecture**: DeepSeek-MoE Transformer-based language model
|
| 31 |
+
- **Combination Method**: Merged model weights from DeepSeek-R1 and DeepSeek-V3 (0324)
|
| 32 |
+
- **Release Date**: 2025-04-27
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
## Contact
|
| 36 |
+
|
| 37 |
+
- Email: [email protected]
|