github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-13 22:15:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add chatglm2-6b support

Browse Source
This commit is contained in:
csunny 2023-06-25 23:05:50 +08:00
parent 2f3a06011a
commit fc7cb1cce3
3 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docs/getting_started/getting_started.md
View File

@ -38,6 +38,7 @@ Once the environment is installed, we have to create a new folder "models" in th
git clone https://huggingface.co/Tribbiani/vicuna-13b git clone https://huggingface.co/Tribbiani/vicuna-13b
git clone https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 git clone https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese git clone https://huggingface.co/GanymedeNil/text2vec-large-chinese
git clone https://huggingface.co/THUDM/chatglm2-6b
``` ```
The model files are large and will take a long time to download. During the download, let's configure the .env file, which needs to be copied and created from the .env.template The model files are large and will take a long time to download. During the download, let's configure the .env file, which needs to be copied and created from the .env.template

6
docs/modules/llms.md
View File

@ -17,6 +17,12 @@ if you want use other model, such as chatglm-6b, you just need update .env confi
``` ```
LLM_MODEL=chatglm-6b LLM_MODEL=chatglm-6b
``` ```
or chatglm2-6b, which is the second-generation version of the open-source bilingual (Chinese-English) chat model ChatGLM-6B.
```
LLM_MODEL=chatglm2-6b
```
## Run Model with cpu. ## Run Model with cpu.
we alse support smaller models, like gpt4all. you can use it with cpu/mps(M1/M2), Download from [gpt4all model](https://gpt4all.io/models/ggml-gpt4all-j-v1.3-groovy.bin) we alse support smaller models, like gpt4all. you can use it with cpu/mps(M1/M2), Download from [gpt4all model](https://gpt4all.io/models/ggml-gpt4all-j-v1.3-groovy.bin)

1
pilot/configs/model_config.py
View File

@ -39,6 +39,7 @@ LLM_MODEL_CONFIG = {
"codet5p-2b": os.path.join(MODEL_PATH, "codet5p-2b"), "codet5p-2b": os.path.join(MODEL_PATH, "codet5p-2b"),
"chatglm-6b-int4": os.path.join(MODEL_PATH, "chatglm-6b-int4"), "chatglm-6b-int4": os.path.join(MODEL_PATH, "chatglm-6b-int4"),
"chatglm-6b": os.path.join(MODEL_PATH, "chatglm-6b"), "chatglm-6b": os.path.join(MODEL_PATH, "chatglm-6b"),
"chatglm2-6b": os.path.join(MODEL_PATH, "chatglm2-6b"),
"text2vec-base": os.path.join(MODEL_PATH, "text2vec-base-chinese"), "text2vec-base": os.path.join(MODEL_PATH, "text2vec-base-chinese"),
"guanaco-33b-merged": os.path.join(MODEL_PATH, "guanaco-33b-merged"), "guanaco-33b-merged": os.path.join(MODEL_PATH, "guanaco-33b-merged"),
"falcon-40b": os.path.join(MODEL_PATH, "falcon-40b"), "falcon-40b": os.path.join(MODEL_PATH, "falcon-40b"),