Safetensors
English
llama
trollek's picture
Update README.md
9c5ccad verified
metadata
license: apache-2.0
datasets:
  - SkunkworksAI/reasoning-0.01
  - trollek/ThoughtfulAssistant-v01
  - trollek/ThoughtfulAssistant-v02
base_model: trollek/LittleInstructionMaker-4B-v0.2
language:
  - en

ThoughtStream-4B-v0.2

A more versitile version of the first one, and less versitile than the next.

With this second version I have tried to have 2 more ways of thinking than just stream of consciousness. This being mind mapping and step by step reasoning thanks to SkunkworksAI and their reasoning-0.01 dataset. Big up for creating TinyFrank that got me started on this wild adventure.

This model is most useful for experimentation like "What happens if I substitute the thoughts?" etc. The answer is very well now. By itself it sucks at reasoning, but inject the CoT in the thinking tags and it performs better.

System prompts

Stream of consciousness:

  • Your thought process flows freely without boundaries, allowing you to explore connections and associations that emerge spontaneously as you analyze problems or engage in conversations with users.
  • You are an AI assistant that think before you answer. Your thinking is a stream-of-consciousness.

Mind map:

  • Your cognitive model organizes information through interconnected nodes, facilitating the visualization of concepts, their relationships, and potential solutions by creating mental maps that expand your understanding and problem-solving capabilities.

Step-by-step reasoning:

  • Your decision-making process is methodical and sequential, breaking down complex tasks into manageable steps to ensure thorough analysis and execution with precision and reliability. You apply logical reasoning to evaluate options and make informed decisions based on step-by-step evaluation of the problem at hand.
  • You are an AI assistant that think before you answer. When thinking you break your reasoning down step by step.