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

Merge pull request #3 from bklieger-groq/feat/improve-docs

Browse Source 
Feat/improve docs
This commit is contained in:
Benjamin Klieger 2024-09-15 19:04:15 -07:00 committed by GitHub
commit 2a99db6070
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 27 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
README.md
View File

@ -4,7 +4,10 @@
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.
g1 is experimental and being open sourced to help inspire the open source community to develop new strategies to produce o1-like reasoning. This is an experiment to show the power of prompting reasoning in visualized steps, not a comparison to or full replication of o1, which uses different techniques. Let's build!
g1 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.
g1 demonstrates the potential of prompting alone to overcome straightforward LLM logic issues like the Strawberry problem, allowing existing open source models to benefit from dynamic reasoning chains and an improved interface for exploring them.
### Examples
@ -30,6 +33,8 @@ Result:
### Quickstart
To use the Streamlit UI, follow these instructions:
~~~
python3 -m venv venv
~~~
@ -50,6 +55,22 @@ export GROQ_API_KEY=gsk...
streamlit run app.py
~~~
---
Alternatively, follow these additional instructions to use the Gradio UI:
~~~
cd gradio
~~~
~~~
pip3 install -r requirements.txt
~~~
~~~
python3 app.py
~~~
### Prompting Strategy
@ -101,6 +122,11 @@ In all-caps to improve prompt compliance by emphesizing the importance of the in
Finally, after the problem is added as a user message, an assistant message is loaded to provide a standardized starting point for the LLM's generation.
> Assistant: Thank you! I will now think step by step following my instructions, starting at the beginning after decomposing the problem
### Credits
This app was developed by [Benjamin Klieger](https://x.com/benjaminklieger).