Update README.md
Browse files
README.md
CHANGED
|
@@ -72,7 +72,7 @@ Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hou
|
|
| 72 |
In addition, its training process is remarkably stable.
|
| 73 |
Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks.
|
| 74 |
<p align="center">
|
| 75 |
-
<img width="80%" src="figures/benchmark.png">
|
| 76 |
</p>
|
| 77 |
|
| 78 |
## 2. Model Summary
|
|
|
|
| 72 |
In addition, its training process is remarkably stable.
|
| 73 |
Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks.
|
| 74 |
<p align="center">
|
| 75 |
+
<img width="80%" src="https://huggingface.co/deepseek-ai/DeepSeek-V3/resolve/main/figures/benchmark.png">
|
| 76 |
</p>
|
| 77 |
|
| 78 |
## 2. Model Summary
|