Safetensors
English
llama
trollek commited on
Commit
14bd26c
·
verified ·
1 Parent(s): c65e72b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -4
README.md CHANGED
@@ -2,10 +2,38 @@
2
  license: apache-2.0
3
  datasets:
4
  - SkunkworksAI/reasoning-0.01
5
- base_model:
6
- - trollek/ThoughtStream-4B-v0.1
7
- - trollek/LittleInstructionMaker-4B-v0.1
8
  ---
9
  # ThoughtStream-4B-v0.2
10
 
11
- A more versitile version of the first one, and less versitile than the next.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: apache-2.0
3
  datasets:
4
  - SkunkworksAI/reasoning-0.01
5
+ - trollek/ThoughtfulAssistant-v01
6
+ base_model: trollek/LittleInstructionMaker-4B-v0.2
 
7
  ---
8
  # ThoughtStream-4B-v0.2
9
 
10
+ A more versitile version of [the first one](https://huggingface.co/trollek/ThoughtStream-4B-v0.1), and less versitile than the next[.](https://www.youtube.com/watch?v=dQw4w9WgXcQ "I swear my name makes sense in Danish, but.. I mean..") This can not compete with [Matt Shumer's](https://huggingface.co/mattshumer) [Reflection](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B), which be wildin' yo. But creating a dataset to "Please find errors and hallucinations in the thought process" is a tad harder than expected™. It is brilliant! And hard! Living in the future is great!
11
+
12
+ 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](https://huggingface.co/SkunkworksAI) and their [reasoning-0.01](https://huggingface.co/datasets/SkunkworksAI/reasoning-0.01) dataset. Big up for creating [TinyFrank](https://huggingface.co/SkunkworksAI/tinyfrank-1.4B) that got me started on this wild adventure.
13
+
14
+ ## System prompts
15
+
16
+ **Stream of consciousness:**
17
+
18
+ - `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.`
19
+ - `You are an AI assistant that think before you answer. Your thinking is a stream-of-consciousness.`
20
+
21
+ **Mind map:**
22
+
23
+ - `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.`
24
+
25
+ **Step-by-step reasoning:**
26
+
27
+ - `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.`
28
+ - `You are an AI assistant that think before you answer. When thinking you break your reasoning down step by step.`
29
+
30
+
31
+ ## Config
32
+
33
+ ```jinja
34
+
35
+
36
+ ```
37
+
38
+ ## Training results
39
+