github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-06-25 15:02:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update gpt4all_faq.md

Browse Source 
- Add information about AVX/AVX2.
- Update supported architectures.

Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
This commit is contained in:
cosmic-snow 2023-07-12 16:23:04 +02:00 committed by AT
parent 6c4f449b7a
commit 00a945eaee
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
gpt4all-bindings/python/docs/gpt4all_faq.md
View File

@ -2,11 +2,13 @@
## What models are supported by the GPT4All ecosystem? ## What models are supported by the GPT4All ecosystem?
Currently, there are three different model architectures that are supported: Currently, there are five different model architectures that are supported:
1. GPTJ - Based off of the GPT-J architecture with examples found [here](https://huggingface.co/EleutherAI/gpt-j-6b) 1. GPT-J - Based off of the GPT-J architecture with examples found [here](https://huggingface.co/EleutherAI/gpt-j-6b)
2. LLAMA - Based off of the LLAMA architecture with examples found [here](https://huggingface.co/models?sort=downloads&search=llama) 2. LLaMA - Based off of the LLaMA architecture with examples found [here](https://huggingface.co/models?sort=downloads&search=llama)
3. MPT - Based off of Mosaic ML's MPT architecture with examples found [here](https://huggingface.co/mosaicml/mpt-7b) 3. MPT - Based off of Mosaic ML's MPT architecture with examples found [here](https://huggingface.co/mosaicml/mpt-7b)
4. Replit - Based off of Replit Inc.'s Replit architecture with examples found [here](https://huggingface.co/replit/replit-code-v1-3b)
5. Falcon - Based off of TII's Falcon architecture with examples found [here](https://huggingface.co/tiiuae/falcon-40b)
## Why so many different architectures? What differentiates them? ## Why so many different architectures? What differentiates them?
@ -25,6 +27,10 @@ The upstream [llama.cpp](https://github.com/ggerganov/llama.cpp) project has int
Fortunately, we have engineered a submoduling system allowing us to dynamically load different versions of the underlying library so that Fortunately, we have engineered a submoduling system allowing us to dynamically load different versions of the underlying library so that
GPT4All just works. GPT4All just works.
## What are the system requirements?
Your CPU needs to support [AVX or AVX2 instructions](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions) and you need enough RAM to load a model into memory.
## What about GPU inference? ## What about GPU inference?
In newer versions of llama.cpp, there has been some added support for NVIDIA GPU's for inference. We're investigating how to incorporate this into our downloadable installers. In newer versions of llama.cpp, there has been some added support for NVIDIA GPU's for inference. We're investigating how to incorporate this into our downloadable installers.