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">Please support me: Ko-fi</a></p>
    </div>
<!-- header end -->

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

Version 2 is focused on writing plots and not gasslighting users with "funny" opiniated chitchat like the short-lived Version 1.
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 becoming one trick pony. (Now that's collocation cliche!)

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.

Also GGUF here: https://huggingface.co/FPHam/PlotBot-V2-13b-GGUF

There is a V3 here: https://huggingface.co/FPHam/Plot_BOT_V3_13b_GPTQ

V3 is not a replacement for V2, it's just different.

**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.
I think of it as sucking the plain text soul...

It is geared towards sci-fi and fantasy but can extrapolate any style. 

**Plagiarism warning**

Being LLM and LLama, the model can borrow subplots and tropes from exisitng works and can also associate names that exists in literature. That's nothing new of course, I'm just reminding you when you meet John Snow on some frozen plannet and he really wants to fly dragon.