Instructions to use FPHam/PlotBot_13B-GPTQ-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/PlotBot_13B-GPTQ-V2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="FPHam/PlotBot_13B-GPTQ-V2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FPHam/PlotBot_13B-GPTQ-V2")
model = AutoModelForCausalLM.from_pretrained("FPHam/PlotBot_13B-GPTQ-V2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FPHam/PlotBot_13B-GPTQ-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/PlotBot_13B-GPTQ-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/PlotBot_13B-GPTQ-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FPHam/PlotBot_13B-GPTQ-V2

SGLang

How to use FPHam/PlotBot_13B-GPTQ-V2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FPHam/PlotBot_13B-GPTQ-V2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/PlotBot_13B-GPTQ-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FPHam/PlotBot_13B-GPTQ-V2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/PlotBot_13B-GPTQ-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FPHam/PlotBot_13B-GPTQ-V2 with Docker Model Runner:
```
docker model run hf.co/FPHam/PlotBot_13B-GPTQ-V2
```

Please support me: Ko-fi

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.

Downloads last month: 69