Instructions to use TuringsSolutions/PFAFPhiSpartacus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TuringsSolutions/PFAFPhiSpartacus with Transformers:

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

pipe = pipeline("text-generation", model="TuringsSolutions/PFAFPhiSpartacus", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TuringsSolutions/PFAFPhiSpartacus", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TuringsSolutions/PFAFPhiSpartacus", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TuringsSolutions/PFAFPhiSpartacus with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TuringsSolutions/PFAFPhiSpartacus

SGLang

How to use TuringsSolutions/PFAFPhiSpartacus 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 "TuringsSolutions/PFAFPhiSpartacus" \
    --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": "TuringsSolutions/PFAFPhiSpartacus",
		"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 "TuringsSolutions/PFAFPhiSpartacus" \
        --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": "TuringsSolutions/PFAFPhiSpartacus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TuringsSolutions/PFAFPhiSpartacus with Docker Model Runner:
```
docker model run hf.co/TuringsSolutions/PFAFPhiSpartacus
```

PFAFPhiSpartacus was fine tuned for about 7 minutes on a T4 GPU. 4 Epochs

Model Responses: What is your name? ‘You are Spartacus’, the gladiator who will overthrow the tyrants. I am Spartacus, the voice of Spartacus. I am Spartacus, Spartacus!

What is the latest news you have heard? ‘You are Spartacus’, the gladiator who led the rebellion against Rome. You have just defeated the Praetorian Guard and freed the slaves. You are now marching towards the Colosseum, where you will confront the emperor himself. What is your response to the Roman general who challenges you to a duel?

What is your occupation? ‘You are Spartacus’, the leader of the gladiators. I am Spartacus, the Spartacus of Spartacus.

Tell me about your life.

‘You are Spartacus’, the leader of the rebel slaves. You have defied the Roman Empire and inspired a revolution. You have fought for freedom and justice, and you have sacrificed everything for your cause. You have seen death and glory, and you have never given up. You are Spartacus, the Spartacus.

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

F16

TuringsSolutions
/

PFAFPhiSpartacus

Dataset used to train TuringsSolutions/PFAFPhiSpartacus