Instructions to use AlbertoB12/Stoicism2_Llama3.1-8b-16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlbertoB12/Stoicism2_Llama3.1-8b-16bit with Transformers:

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

pipe = pipeline("text-generation", model="AlbertoB12/Stoicism2_Llama3.1-8b-16bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlbertoB12/Stoicism2_Llama3.1-8b-16bit")
model = AutoModelForCausalLM.from_pretrained("AlbertoB12/Stoicism2_Llama3.1-8b-16bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AlbertoB12/Stoicism2_Llama3.1-8b-16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlbertoB12/Stoicism2_Llama3.1-8b-16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlbertoB12/Stoicism2_Llama3.1-8b-16bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AlbertoB12/Stoicism2_Llama3.1-8b-16bit

SGLang

How to use AlbertoB12/Stoicism2_Llama3.1-8b-16bit 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 "AlbertoB12/Stoicism2_Llama3.1-8b-16bit" \
    --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": "AlbertoB12/Stoicism2_Llama3.1-8b-16bit",
		"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 "AlbertoB12/Stoicism2_Llama3.1-8b-16bit" \
        --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": "AlbertoB12/Stoicism2_Llama3.1-8b-16bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use AlbertoB12/Stoicism2_Llama3.1-8b-16bit 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 AlbertoB12/Stoicism2_Llama3.1-8b-16bit 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 AlbertoB12/Stoicism2_Llama3.1-8b-16bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlbertoB12/Stoicism2_Llama3.1-8b-16bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="AlbertoB12/Stoicism2_Llama3.1-8b-16bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use AlbertoB12/Stoicism2_Llama3.1-8b-16bit with Docker Model Runner:
```
docker model run hf.co/AlbertoB12/Stoicism2_Llama3.1-8b-16bit
```

Stoicism Language Model 2 StLM (Marcus Aurelius, Seneca, Epictetus)

This language model has been fine-tuned with a specialized dataset based on the teachings of Stoic philosophers, including Marcus Aurelius, Seneca, and Epictetus. It captures the essence of Stoic philosophy, offering thoughtful, reflective responses grounded in Stoic principles and keeping the Stoic language and style. Ideal for anyone interested in Stoic wisdom, personal growth, and philosophical discussions, the model can assist in navigating life's challenges with resilience, virtue, and reason.

The model is trained to deliver answers rooted in Stoic thought, providing practical guidance on topics such as emotional control, mindfulness, perseverance, and the pursuit of wisdom. It is well-suited for applications that aim to integrate ancient philosophical insights into modern-day problem-solving, whether through virtual Stoic coaches, AI-powered personal growth tools, or interactive philosophical discussions.

This fine-tuned model is perfect for users seeking advice on managing stress, building mental resilience, and developing a mindset focused on self-control, rationality, and virtue, as advocated by the Stoic philosophers. Whether for meditation, journaling, or day-to-day decision-making, the model brings timeless wisdom to help users lead a more mindful and fulfilling life.