diff --git a/docs/getting_started/getting_started.md b/docs/getting_started/getting_started.md index d082a0c75..33653f248 100644 --- a/docs/getting_started/getting_started.md +++ b/docs/getting_started/getting_started.md @@ -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/sentence-transformers/all-MiniLM-L6-v2 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 diff --git a/docs/modules/llms.md b/docs/modules/llms.md index 217961a51..bec64313e 100644 --- a/docs/modules/llms.md +++ b/docs/modules/llms.md @@ -17,6 +17,12 @@ if you want use other model, such as chatglm-6b, you just need update .env confi ``` 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. 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) diff --git a/pilot/configs/model_config.py b/pilot/configs/model_config.py index f6d59e4e1..2f44fc520 100644 --- a/pilot/configs/model_config.py +++ b/pilot/configs/model_config.py @@ -39,6 +39,7 @@ LLM_MODEL_CONFIG = { "codet5p-2b": os.path.join(MODEL_PATH, "codet5p-2b"), "chatglm-6b-int4": os.path.join(MODEL_PATH, "chatglm-6b-int4"), "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"), "guanaco-33b-merged": os.path.join(MODEL_PATH, "guanaco-33b-merged"), "falcon-40b": os.path.join(MODEL_PATH, "falcon-40b"),