|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
The models can be loaded by the [InferLLM](https://github.com/MegEngine/InferLLM) project. |
|
|
|
|
|
Chinese Alpaca model is from https://github.com/ymcui/Chinese-LLaMA-Alpaca |
|
|
|
|
|
ggml Alpaca model is from https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml/tree/main |
|
|
|
|
|
the two models also can be loaded by the [llama.cpp](https://github.com/ggerganov/llama.cpp) project. |
|
|
|
|
|
InferLLM support the ChatGLM/ChatGLM2 model, the chatglm-q4/bin/chatglm2-q4.bin is the int4 quantized model from [chatglm-6b](https://huggingface.co/THUDM/chatglm-6b)/[chatglm2-6b](https://huggingface.co/THUDM/chatglm2-6b) |
|
|
|
|
|
InferLLM support the baichuan model, the baichuan-q4 is the int4 quantized model from [baichuan](https://huggingface.co/fireballoon/baichuan-vicuna-7b) |
|
|
|
|
|
InferLLM support the llama2 model, the llama2-q4 is the int4 quantized model from [llama2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) |
|
|
|
