tcsenpai/multi1
1
0
Fork 0
mirror of https://github.com/tcsenpai/multi1.git synced 2025-06-06 19:15:23 +00:00
Code Issues 4 Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
TheCookingSenpai 2024-09-18 11:42:54 +02:00 committed by GitHub
parent 7ed4e99d7f
commit 1b8387c043
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -1,11 +1,12 @@
# multi1: Using multiple AI providers to create o1-like reasoning chains # multi1: Using multiple AI providers to create o1-like reasoning chains
***IMPORTANT: multi1 is a fork of [g1](https://github.com/bklieger-groq/g1/), made by [Benjamin Klieger](https://x.com/benjaminklieger). It was made as a way to experiment with multiple AI providers included local LLMs. All credits go to the original author.*** This is an early prototype of using prompting strategies to improve the LLM's reasoning capabilities through o1-like reasoning chains. This allows the LLM to "think" and solve logical problems that usually otherwise stump leading models. Unlike o1, all the reasoning tokens are shown.
## Features ## Features
- [x] Using an unified interface to try out different providers - [x] Using an unified interface to try out different providers
- [x] Configuring the app from the sidebar - [x] Configuring the app from the sidebar
- [x] Modular design for quick provider adding
## Providers ## Providers
@ -17,6 +18,7 @@
- [ ] Add more providers - [ ] Add more providers
- [ ] Possibly use LiteLLM instead of defining each provider - [ ] Possibly use LiteLLM instead of defining each provider
- [ ] Create a guide to quickly add providers
## Example ## Example
@ -24,6 +26,8 @@
## Description ## Description
***IMPORTANT: multi1 is a fork of [g1](https://github.com/bklieger-groq/g1/), made by [Benjamin Klieger](https://x.com/benjaminklieger). It was made as a way to experiment with multiple AI providers included local LLMs. All credits go to the original author.***
This is an early prototype of using prompting strategies to improve the LLM's reasoning capabilities through o1-like reasoning chains. This allows the LLM to "think" and solve logical problems that usually otherwise stump leading models. Unlike o1, all the reasoning tokens are shown, and the app uses an open source model. This is an early prototype of using prompting strategies to improve the LLM's reasoning capabilities through o1-like reasoning chains. This allows the LLM to "think" and solve logical problems that usually otherwise stump leading models. Unlike o1, all the reasoning tokens are shown, and the app uses an open source model.
multi1 is experimental and being open sourced to help inspire the open source community to develop new strategies to produce o1-like reasoning. This experiment helps show the power of prompting reasoning in visualized steps, not a comparison to or full replication of o1, which uses different techniques. OpenAI's o1 is instead trained with large-scale reinforcement learning to reason using Chain of Thought, achieving state-of-the-art performance on complex PhD-level problems. multi1 is experimental and being open sourced to help inspire the open source community to develop new strategies to produce o1-like reasoning. This experiment helps show the power of prompting reasoning in visualized steps, not a comparison to or full replication of o1, which uses different techniques. OpenAI's o1 is instead trained with large-scale reinforcement learning to reason using Chain of Thought, achieving state-of-the-art performance on complex PhD-level problems.