diff --git a/README.md b/README.md index a5944cd4..9af511b9 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,5 @@

GPT4All

Demo, data, and code to train open-source assistant-style large language model based on GPT-J and LLaMa

-

:green_book: Technical Report 2: GPT4All-J

@@ -26,6 +25,23 @@

+

+Discord +

+ +

+:computer: Official Typescript Bindings +

+ +

+:speech_balloon: Official Chat Interface +

+ +

+🦜️🔗 Official Langchain Backend +

+ +

Discord

@@ -82,6 +98,8 @@ accelerate launch --dynamo_backend=inductor --num_processes=8 --num_machines=1 - # Original GPT4All Model (based on GPL Licensed LLaMa) + + ![gpt4all-lora-demo](https://user-images.githubusercontent.com/13879686/228352356-de66ca7a-df70-474e-b929-2e3656165051.gif) Run on M1 Mac (not sped up!) @@ -165,8 +183,8 @@ Feel free to convert this to a more structured table. # Roadmap ## Short Term - - (IN PROGRESS) Train a GPT4All model based on GPTJ to alleviate llama distribution issues. - - (IN PROGRESS) Create improved CPU and GPU interfaces for this model. + - (Done) Train a GPT4All model based on GPTJ to alleviate llama distribution issues. + - (Done) Create improved CPU and GPU interfaces for this model. - (Done) [Integrate llama.cpp bindings](https://github.com/nomic-ai/pyllamacpp) - (Done) [Create a good conversational chat interface for the model.](https://github.com/nomic-ai/gpt4all-ui) - (Done) [Allow users to opt in and submit their chats for subsequent training runs](https://github.com/nomic-ai/gpt4all-ui) @@ -174,7 +192,7 @@ Feel free to convert this to a more structured table. ## Medium Term - (NOT STARTED) Integrate GPT4All with [Atlas](https://atlas.nomic.ai) to allow for document retrieval. - BLOCKED by GPT4All based on GPTJ - - (NOT STARTED) Integrate GPT4All with Langchain. + - (Done) Integrate GPT4All with Langchain. - (IN PROGRESS) Build easy custom training scripts to allow users to fine tune models. ## Long Term