JakeTurner616 commited on
Commit
8088a40
1 Parent(s): 9081f77

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -0
README.md CHANGED
@@ -1,3 +1,40 @@
1
  ---
2
  license: mit
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ base_model: EleutherAI/gpt-neo-1.3B
4
  ---
5
+ # Adonalsium-gpt
6
+
7
+ ## Basic Information
8
+
9
+ - **Model Name**: Adonalsium-gpt-neo-1.3B
10
+ - **Model Type**: Text Generation
11
+ - **Developers**: [Jake T](https://github.com/JakeTurner616/), [Ilijah P](https://github.com/IlijahP/)
12
+ - **Contact Information**: [email protected], [Github repo](https://github.com/JakeTurner616/Adonalsium)
13
+ - **Model Data Source**: Cosmere series novels by Brandon Sanderson. Dataset and workflows can be found [here](https://github.com/IlijahP/Adonalsium)
14
+ - **Data Visualization**: [Cosmere Character Visualization](https://serverboi.org/Adonalsium/)
15
+ - **Training and Generation Notebook**: [Google Colab Notebook](https://colab.research.google.com/github/JakeTurner616/Adonalsium/blob/LLM/trainandgenerate_1_3B.ipynb)
16
+
17
+ ## Overview
18
+
19
+ This LLM was trained as an attempt to generate text that mirrors the complex narrative and character interactions of Brandon Sanderson's Cosmere series, aiming to enhance creative storytelling and facilitate academic research in narrative analysis.
20
+
21
+ ## Data Source
22
+
23
+ The model leverages comprehensive datasets derived from the entire Cosmere series, enriched by dynamic visualizations that highlight the complex interplay of relationships and interactions within the Cosmere universe.
24
+
25
+ ## Technical Details
26
+
27
+ - **Environment**: Google Colab
28
+ - **Architecture**: Adaptations of GPT-2/GPT-3 tailored for Cosmere narratives
29
+ - **Training Data**: Cosmere series
30
+
31
+ | Step | Training Loss |
32
+ |------|---------------|
33
+ | 500 | 2.592800 |
34
+ | 1000 | 2.382900 |
35
+
36
+ Detailed technical specifics, including architecture choices, hyperparameters, and training methodologies, are documented in the accompanying [training and generation notebook](https://colab.research.google.com/github/JakeTurner616/Adonalsium/blob/LLM/trainandgenerate_1_3B.ipynb).
37
+
38
+ ## Access and Usage
39
+
40
+ The model is accessible for use as detailed in the [training and generation notebook](https://colab.research.google.com/github/JakeTurner616/Adonalsium/blob/LLM/trainandgenerate_1_3B.ipynb), designed to streamline adoption for creative and research endeavors within the Cosmere thematic universe.