Skip to content

Commit

Permalink
doc:add llm use faq (#584)
Browse files Browse the repository at this point in the history
  • Loading branch information
fangyinc authored Sep 14, 2023
2 parents 94c4f4a + 423d63e commit f21d542
Show file tree
Hide file tree
Showing 19 changed files with 96 additions and 7 deletions.
2 changes: 1 addition & 1 deletion docs/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
copyright = "2023, csunny"
author = "csunny"

version = "👏👏 0.3.6"
version = "👏👏 0.3.8"
html_title = project + " " + version

# -- General configuration ---------------------------------------------------
Expand Down
37 changes: 36 additions & 1 deletion docs/getting_started/faq/llm/llm_faq.md
Original file line number Diff line number Diff line change
Expand Up @@ -49,4 +49,39 @@ You can modify the setting `QUANTIZE_8bit=True` or `QUANTIZE_4bit=True` in `.env

Llama-2-70b with 8-bit quantization can run with 80 GB of VRAM, and 4-bit quantization can run with 48 GB of VRAM.

Note: you need to install the latest dependencies according to [requirements.txt](https://github.com/eosphoros-ai/DB-GPT/blob/main/requirements.txt).
Note: you need to install the latest dependencies according to [requirements.txt](https://github.com/eosphoros-ai/DB-GPT/blob/main/requirements.txt).

##### Q5 How to Add LLM Service dynamic local mode

Now DB-GPT through multi-llm service switch, so how to add llm service dynamic,

```commandline
dbgpt model start --model_name ${your_model_name} --model_path ${your_model_path}
chatglm2-6b
eg: dbgpt model start --model_name chatglm2-6b --model_path /root/DB-GPT/models/chatglm2-6b
chatgpt
eg: dbgpt model start --model_name chatgpt_proxyllm --model_path chatgpt_proxyllm --proxy_api_key ${OPENAI_KEY} --proxy_server_url {OPENAI_URL}
```
##### Q6 How to Add LLM Service dynamic in remote mode
If you deploy llm service in remote machine instance, and you want to add model service to dbgpt server to manage

use dbgpt start worker and set --controller_addr.

```commandline
eg: dbgpt start worker --model_name vicuna-13b-v1.5 \
--model_path /app/models/vicuna-13b-v1.5 \
--port 8002 \
--controller_addr http://127.0.0.1:8000
```


##### Q7 dbgpt command not found

```commandline
pip install -e .
```


25 changes: 21 additions & 4 deletions docs/locales/zh_CN/LC_MESSAGES/getting_started/faq/llm/llm_faq.po
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-09-13 23:04+0800\n"
"POT-Creation-Date: 2023-09-14 14:35+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
Expand Down Expand Up @@ -120,7 +120,8 @@ msgid ""
msgstr ""

#: ../../getting_started/faq/llm/llm_faq.md:54 5fe0d9ced7e848799f4d7bce92a5c130
msgid "Q5 How to Add LLM Service dynamic"
#, fuzzy
msgid "Q5 How to Add LLM Service dynamic local mode"
msgstr "Q5 怎样动态新增模型服务"

#: ../../getting_started/faq/llm/llm_faq.md:56 fd921148e3e547beb6c74035a6b6a8b0
Expand All @@ -129,7 +130,23 @@ msgid ""
"dynamic,"
msgstr "DB-GPT支持多个模型服务切换, 怎样添加一个模型服务呢"

#: ../../getting_started/faq/llm/llm_faq.md:68 f8c024339da447ce8160a4eb9f87c125
msgid "Q6 dbgpt command not found"
#: ../../getting_started/faq/llm/llm_faq.md:67 5fe0d9ced7e848799f4d7bce92a5c130
#, fuzzy
msgid "Q6 How to Add LLM Service dynamic in remote mode"
msgstr "Q5 怎样动态新增模型服务"

#: ../../getting_started/faq/llm/llm_faq.md:68 bd29cd6d29a64908af15b391d73ea82a
msgid ""
"If you deploy llm service in remote machine instance, and you want to "
"add model service to dbgpt server to manage"
msgstr "如果你想在远程机器实例部署大模型服务并添加到本地dbgpt_server进行管理"

#: ../../getting_started/faq/llm/llm_faq.md:70 ace16dfc4326431dbe4a9a32e4a83ba4
msgid "use dbgpt start worker and set --controller_addr."
msgstr "使用1`dbgpt start worker`命令并设置注册地址--controller_addr"

#: ../../getting_started/faq/llm/llm_faq.md:81 f8c024339da447ce8160a4eb9f87c125
#, fuzzy
msgid "Q7 dbgpt command not found"
msgstr "Q6 dbgpt command not found"

Binary file added pilot/server/static/models/baichuan.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/bard.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/chatglm.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/chatgpt.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/claude.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/falcon.jpeg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/google.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/gorilla.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
37 changes: 37 additions & 0 deletions pilot/server/static/models/huggingface.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/llama.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/qwen2.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/salesforce.jpeg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/vicuna.jpeg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/wizardlm.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added pilot/server/static/models/zhipu.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
2 changes: 1 addition & 1 deletion setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -347,7 +347,7 @@ def init_install_requires():
setuptools.setup(
name="db-gpt",
packages=find_packages(exclude=("tests", "*.tests", "*.tests.*", "examples")),
version="0.3.6",
version="0.3.8",
author="csunny",
author_email="[email protected]",
description="DB-GPT is an experimental open-source project that uses localized GPT large models to interact with your data and environment."
Expand Down

0 comments on commit f21d542

Please sign in to comment.