2023-03-28 03:20:59 +03:00
< h1 align = "center" > GPT4All< / h1 >
2024-07-01 20:00:14 +03:00
< p align = "center" > GPT4All runs large language models (LLMs) privately on everyday desktops & laptops. < br > < br > No API calls or GPUs required - you can just download the application and < a href = "https://docs.gpt4all.io/gpt4all_desktop/quickstart.html#quickstart" > get started< / a >
2023-05-10 19:05:42 +03:00
< p align = "center" >
2024-07-01 20:00:14 +03:00
< a href = "https://gpt4all.io/installers/gpt4all-installer-win64.exe" >
< img src = "gpt4all-bindings/python/docs/assets/windows.png" width = "80" height = "80" > < br >
Download for Windows
< / a >
2023-05-10 19:05:42 +03:00
< / p >
2024-07-01 20:00:14 +03:00
2023-03-29 04:07:04 +03:00
< p align = "center" >
2024-07-01 20:00:14 +03:00
< a href = "https://gpt4all.io/installers/gpt4all-installer-darwin.dmg" >
< img src = "gpt4all-bindings/python/docs/assets/mac.png" width = "80" height = "90" > < br >
Download for MacOS
< / a >
2023-03-29 04:07:04 +03:00
< / p >
2024-07-01 20:00:14 +03:00
2024-05-03 03:02:19 +03:00
< p align = "center" >
2024-07-01 20:00:14 +03:00
< a href = "https://gpt4all.io/installers/gpt4all-installer-linux.run" >
< img src = "gpt4all-bindings/python/docs/assets/linux.png" width = "80" height = "80" > < br >
Download for Linux
< / a >
2024-05-03 03:02:19 +03:00
< / p >
2024-07-01 20:00:14 +03:00
2023-04-13 21:33:52 +03:00
< p align = "center" >
2024-07-01 20:00:14 +03:00
< a href = "https://gpt4all.io" > Website< / a > • < a href = "https://docs.gpt4all.io" > Documentation< / a > • < a href = "https://discord.gg/mGZE39AS3e" > Discord< / a >
2023-04-13 21:33:52 +03:00
< / p >
2024-03-18 05:34:19 +03:00
< p align = "center" >
2024-07-01 20:00:14 +03:00
< a href = "https://forms.nomic.ai/gpt4all-release-notes-signup" > Subscribe to the newsletter< / a >
2024-03-18 05:34:19 +03:00
< / p >
2023-05-13 15:02:06 +03:00
< p align = "center" >
2024-07-01 20:00:14 +03:00
GPT4All is made possible by our compute partner < a href = "https://www.paperspace.com/" > Paperspace< / a > .
2023-05-13 15:02:06 +03:00
< / p >
< p align = "center" >
2024-07-01 20:00:14 +03:00
< a href = "https://www.phorm.ai/query?projectId=755eecd3-24ad-49cc-abf4-0ab84caacf63" > < img src = "https://img.shields.io/badge/Phorm-Ask_AI-%23F2777A.svg" alt = "phorm.ai" > < / a >
2023-05-13 15:02:06 +03:00
< / p >
2023-04-13 19:56:08 +03:00
2023-10-24 19:12:13 +03:00
2023-04-13 19:56:08 +03:00
2024-07-01 20:00:14 +03:00
## Install GPT4All Python
2023-05-22 23:08:03 +03:00
2024-07-01 20:00:14 +03:00
`gpt4all` gives you access to LLMs with our Python client around [`llama.cpp` ](https://github.com/ggerganov/llama.cpp ) implementations.
2024-05-06 20:29:37 +03:00
2024-07-01 20:00:14 +03:00
Nomic contributes to open source software like [`llama.cpp` ](https://github.com/ggerganov/llama.cpp ) to make LLMs accessible and efficient **for all** .
2023-05-11 19:31:08 +03:00
2024-07-01 20:00:14 +03:00
```bash
pip install gpt4all
```
2024-05-15 21:10:10 +03:00
2024-07-01 20:00:14 +03:00
```python
from gpt4all import GPT4All
model = GPT4All("Meta-Llama-3-8B-Instruct.Q4_0.gguf") # downloads / loads a 4.66GB LLM
with model.chat_session():
print(model.generate("How can I run LLMs efficiently on my laptop?", max_tokens=1024))
```
2024-05-15 21:10:10 +03:00
2024-07-01 20:00:14 +03:00
### Release History
- **July 2nd, 2024**: V3.0.0 Release
- New UI/UX: fresh redesign of the chat application GUI and user experience
- LocalDocs: bring information from files on-device into chats
2023-10-24 19:04:19 +03:00
- **October 19th, 2023**: GGUF Support Launches with Support for:
- Mistral 7b base model, an updated model gallery on [gpt4all.io ](https://gpt4all.io ), several new local code models including Rift Coder v1.5
2024-03-25 18:38:38 +03:00
- [Nomic Vulkan ](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan ) support for Q4\_0 and Q4\_1 quantizations in GGUF.
2023-10-24 19:05:46 +03:00
- Offline build support for running old versions of the GPT4All Local LLM Chat Client.
2024-05-06 20:29:37 +03:00
- **September 18th, 2023**: [Nomic Vulkan ](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan ) launches supporting local LLM inference on NVIDIA and AMD GPUs.
- **July 2023**: Stable support for LocalDocs, a feature that allows you to privately and locally chat with your data.
2024-05-09 19:50:26 +03:00
- **June 28th, 2023**: [Docker-based API server] launches allowing inference of local LLMs from an OpenAI-compatible HTTP endpoint.
2023-05-11 19:31:08 +03:00
2024-05-09 19:50:26 +03:00
[Docker-based API server]: https://github.com/nomic-ai/gpt4all/tree/cef74c2be20f5b697055d5b8b506861c7b997fab/gpt4all-api
2023-10-25 05:03:21 +03:00
2023-08-23 23:53:30 +03:00
### Integrations
2024-07-01 20:00:14 +03:00
* :parrot::link: [Langchain ](https://python.langchain.com/v0.2/docs/integrations/providers/gpt4all/ )
2024-05-06 20:29:37 +03:00
* :card_file_box: [Weaviate Vector Database ](https://github.com/weaviate/weaviate ) - [module docs ](https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-gpt4all )
2024-06-05 18:05:21 +03:00
* :telescope: [OpenLIT (OTel-native Monitoring) ](https://github.com/openlit/openlit ) - [Docs ](https://docs.openlit.io/latest/integrations/gpt4all )
2024-05-06 20:29:37 +03:00
2023-04-13 19:56:08 +03:00
2023-05-13 15:02:06 +03:00
## Contributing
2023-05-14 22:48:17 +03:00
GPT4All welcomes contributions, involvement, and discussion from the open source community!
Please see CONTRIBUTING.md and follow the issues, bug reports, and PR markdown templates.
2023-05-13 15:02:06 +03:00
Check project discord, with project owners, or through existing issues/PRs to avoid duplicate work.
Please make sure to tag all of the above with relevant project identifiers or your contribution could potentially get lost.
Example tags: `backend` , `bindings` , `python-bindings` , `documentation` , etc.
2024-04-17 19:19:57 +03:00
2023-05-22 23:08:03 +03:00
## Technical Reports
< p align = "center" >
< a href = "https://gpt4all.io/reports/GPT4All_Technical_Report_3.pdf" > :green_book: Technical Report 3: GPT4All Snoozy and Groovy < / a >
< / p >
< p align = "center" >
< a href = "https://static.nomic.ai/gpt4all/2023_GPT4All-J_Technical_Report_2.pdf" > :green_book: Technical Report 2: GPT4All-J < / a >
< / p >
< p align = "center" >
< a href = "https://s3.amazonaws.com/static.nomic.ai/gpt4all/2023_GPT4All_Technical_Report.pdf" > :green_book: Technical Report 1: GPT4All< / a >
< / p >
2023-05-13 15:02:06 +03:00
2024-05-06 20:29:37 +03:00
2023-04-13 18:16:31 +03:00
## Citation
2023-03-29 00:31:35 +03:00
2023-04-13 18:16:31 +03:00
If you utilize this repository, models or data in a downstream project, please consider citing it with:
2023-03-28 19:00:25 +03:00
```
@misc {gpt4all,
2023-03-28 21:50:27 +03:00
author = {Yuvanesh Anand and Zach Nussbaum and Brandon Duderstadt and Benjamin Schmidt and Andriy Mulyar},
2023-03-28 19:00:25 +03:00
title = {GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/nomic-ai/gpt4all}},
}
```