Skip to content

Commit 6c37103

Browse files
authored
Update Maturity_Model_for_PaddleLargeModelToolChain_Hardware_Adaptation.md (#974)
update Qwen model version. The previous verison have typos
1 parent 88ed593 commit 6c37103

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

working_groups/Maturity_Model_for_PaddleLargeModelToolChain_Hardware_Adaptation.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -30,9 +30,9 @@
3030
</tr>
3131
</tr>
3232
<td>II级</td>
33-
<td >Qwen2-14B <br>SD(SFT only)</td>
33+
<td >Qwen2.5-14B <br>SD(SFT only)</td>
3434
<td>tokens/TFLOPS (取前1000步均值)达到A100/800的40%</td>
35-
<td>Qwen2-14B<br>SD</td>
35+
<td>Qwen2.5-14B<br>SD</td>
3636
<td> int8 (weight only)</td>
3737
<td>首token 时延不超过1s的QPS/TFPLOPs达到A800的40%</td>
3838
</tr>

0 commit comments

Comments
 (0)