github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-07-31 15:47:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update getting_started.md

Browse Source 
Steps for Starting ChatGLM-6B and ChatGLM2-6B with Multiple Cards
This commit is contained in:
qutcat1997 2023-07-31 18:32:46 +08:00 committed by GitHub
parent f57e6c8ba1
commit 96dfc3798b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/getting_started/getting_started.md
View File

@ -83,6 +83,21 @@ If you want to access an external LLM service, you need to 1.set the variables L
```bash
$ python pilot/server/dbgpt_server.py --light
```
#### 3.1 Steps for Starting ChatGLM-6B and ChatGLM2-6B with Multiple Cards
Modify the. env.template or pilot/configurations/config.py file NUM_ Number of GPUS (quantity is the actual number of graphics cards required for startup)
At the same time, it is necessary to specify the required gpu card ID before starting the command (note that the number of gpu cards specified is consistent with the number of NUM_GPUS), as shown below:
````shell
# Specify 1 gpu card
NUM_GPUS = 1
CUDA_VISIBLE_DEVICES=0 python3 pilot/server/dbgpt_server.py
# Specify 4 gpus card
NUM_GPUS = 4
CUDA_VISIBLE_DEVICES=3,4,5,6 python3 pilot/server/dbgpt_server.py
````
If you want to learn about dbgpt-webui, read https://github.com/csunny/DB-GPT/tree/new-page-framework/datacenter