README.md

---
tags:
- llama
- LLM
---

<!-- header start -->
<div style="display: flex; flex-direction: column; align-items: center;">
</div>  
<div style="width: 100%;">
    <img src="https://huggingface.co/FPHam/PlotBOT_13b-GPTQ-V2/resolve/main/plotbot.jpg" alt="PlotBot" style="width: 50%; min-width: 200px; display: block; margin: auto;">
</div>
<div style="display: flex; flex-direction: column; align-items: center;">
        <p><a href="https://ko-fi.com/Q5Q5MOB4M">Buy Plot-Bot Ko-fi</a></p>
    </div>
<!-- header end -->

## PlotBOT 13b LLama 2 model for writing story plots (Version 2 - strictly plots)

I'm RN uploading version 2 that will be focused on writing plots and not gasslighting users with "funny" opiniated chitchat.
I know it was adorable at first, but everything would ultimately result in sounding the same. That's a bad novelty act.

The experimental V1 was too overtrained on a single style with little variation and it would just repeat the same language cliches and word collocations to the point of being recognizable even by a monkey.

One trick pony. (that's collocation!)

A separate "unhinged" model (for fun) may be released later where I may go the other way, with deeper dataset. 

For now I'll stay away from mixing function and style.

**PlotBOT V2 uses ALPACA instruct**

```
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Write me a plot for sci-fi detective story. The main character name is Elisabeth Windex. She is lonely PI working on the Moon.
 
### Response:
```

**Training**

This is mostly an experiment to test my DEMENTOR plain text learning. DEMENTOR stands for Deep Memorization Enforcement Through Overlapping and Repetition, and I spent good 10 minutes with ChatGPT to come up with that acronym, so shush.