Instructions to use Fizzarolli/phencyclidine-8b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fizzarolli/phencyclidine-8b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Fizzarolli/phencyclidine-8b-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fizzarolli/phencyclidine-8b-v1")
model = AutoModelForCausalLM.from_pretrained("Fizzarolli/phencyclidine-8b-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Fizzarolli/phencyclidine-8b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fizzarolli/phencyclidine-8b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fizzarolli/phencyclidine-8b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Fizzarolli/phencyclidine-8b-v1

SGLang

How to use Fizzarolli/phencyclidine-8b-v1 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 "Fizzarolli/phencyclidine-8b-v1" \
    --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": "Fizzarolli/phencyclidine-8b-v1",
		"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 "Fizzarolli/phencyclidine-8b-v1" \
        --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": "Fizzarolli/phencyclidine-8b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use Fizzarolli/phencyclidine-8b-v1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Fizzarolli/phencyclidine-8b-v1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Fizzarolli/phencyclidine-8b-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Fizzarolli/phencyclidine-8b-v1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Fizzarolli/phencyclidine-8b-v1",
    max_seq_length=2048,
)

Docker Model Runner
How to use Fizzarolli/phencyclidine-8b-v1 with Docker Model Runner:
```
docker model run hf.co/Fizzarolli/phencyclidine-8b-v1
```

phencyclidine v1

experimental "storytelling" and roleplaying finetune of llama 3.

support me on ko-fi!

~~please i need money to stay alive~~

quants

GGUF: https://huggingface.co/Lewdiculous/phencyclidine-8b-v1-GGUF-IQ-Imatrix (thanks @Lewdiculous!)

prompting

storytelling

Title: Story Title
Description: Story Description
Tags: ['tag1', 'tag2', 'tag3', '...']


# Chapter 1
Chapter 1 text...

# Chapter 2
Chapter 2 text...

...

roleplaying

<|description|>Character 1
Character 1 is...</s>
<|description|>Character 2
It might work without this description of Character 2, but I'm not sure...</s>
<|message|>Character 1
Hi!</s>
<|message|>Character 2
Hello!</s>

(no, i didn't make these special tokens. yes, that probably makes the model worse. shush.)
sillytavern templates available for this one! make sure to set both the context template and instruct template. any samplers should work somewhat

datasets

half wattpad, half bluemoon. not enough? eh, probably. at least it generates coherent text tho

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16