Update index.md (#689)

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
This commit is contained in:
Andriy Mulyar
2023-05-22 17:29:01 -07:00
committed by GitHub
parent 46df84a876
commit b40cd065e9

View File

@@ -24,8 +24,11 @@ Most people do not have such a powerful computer or access to GPU hardware. By r
GPT4All models can run on your laptop using only 4-8GB of RAM enabling their wide-spread utility. GPT4All models can run on your laptop using only 4-8GB of RAM enabling their wide-spread utility.
The GPT4All software ecosystem is currently compatible with three variants of the Transformer neural network architecture: The GPT4All software ecosystem is currently compatible with three variants of the Transformer neural network architecture:
- LLaMa - LLaMa
- GPT-J - GPT-J
- MPT - MPT
Any model trained with one of these architectures can be quantized and run locally with all GPT4All bindings and in the Any model trained with one of these architectures can be quantized and run locally with all GPT4All bindings and in the