DeepSeek/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3 synced 2025-06-26 18:17:55 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge pull request #234 from wangfuchun-fc/patch-1

Browse Source 
fix: fix readme doc typo.
This commit is contained in:
Xingkai Yu
2025-01-07 17:53:28 +08:00
committed by GitHub
parent 25109d2ccd 3779a89770
commit ee4c4ea32b
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -283,13 +283,13 @@ python convert.py --hf-ckpt-path /path/to/DeepSeek-V3 --save-path /path/to/DeepS
Then you can chat with DeepSeek-V3:
```shell
torchrun --nnodes 2 --nproc-per-node 8 generate.py --node-rank $RANK --master-addr $ADDR --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --interactive --temperature 0.7 --max-new-tokens 200
torchrun --nnodes 2 --nproc-per-node 8 --node-rank $RANK --master-addr $ADDR generate.py --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --interactive --temperature 0.7 --max-new-tokens 200
```
Or batch inference on a given file:
```shell
torchrun --nnodes 2 --nproc-per-node 8 generate.py --node-rank $RANK --master-addr $ADDR --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --input-file $FILE
torchrun --nnodes 2 --nproc-per-node 8 --node-rank $RANK --master-addr $ADDR generate.py --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --input-file $FILE
```
### 6.2 Inference with SGLang (recommended)