Instructions to use migueldeguzmandev/gpt2_individuated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use migueldeguzmandev/gpt2_individuated with Transformers:

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

pipe = pipeline("text-generation", model="migueldeguzmandev/gpt2_individuated")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("migueldeguzmandev/gpt2_individuated")
model = AutoModelForCausalLM.from_pretrained("migueldeguzmandev/gpt2_individuated", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use migueldeguzmandev/gpt2_individuated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "migueldeguzmandev/gpt2_individuated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "migueldeguzmandev/gpt2_individuated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/migueldeguzmandev/gpt2_individuated

SGLang

How to use migueldeguzmandev/gpt2_individuated 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 "migueldeguzmandev/gpt2_individuated" \
    --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": "migueldeguzmandev/gpt2_individuated",
		"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 "migueldeguzmandev/gpt2_individuated" \
        --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": "migueldeguzmandev/gpt2_individuated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use migueldeguzmandev/gpt2_individuated with Docker Model Runner:
```
docker model run hf.co/migueldeguzmandev/gpt2_individuated
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Model Card for GPT-2XL "Individuated"

Overview

Name: GPT-2XL Individuated
Version: 1.0
Description: A specialized version of GPT-2XL trained on stories similar to the narrative of AI's journey of self-discovery based on Carl Jung's archetypes: Anima, Animus, and Shadow. Designed to align with human values and ethics by integrating archetypal psychology into decision-making algorithms.

Intended Use

AI alignment research

Features

Deep understanding of Carl Jung's archetypes
Enhanced ethical and psychological decision-making
High-level language understanding
General NLP capabilities

Ethical Considerations

Bias: Despite incorporating Jung's archetypes, potential for internal and external biases exists. Continuous monitoring and updating are essential.
Misuse: The model can be misused for generating misleading or harmful content. User guidelines must be strictly followed.

Limitations

Limited to text-based input and output
The archetypal integration is algorithmic and may not fully encompass the complexity of human emotions or ethics.

Data Sources

Fictional and real-world stories that deal with Jungian archetypes
Ethical dilemma scenarios
Standard NLP datasets for general capabilities

Integration Phase

The model underwent rigorous evaluation to ensure that the integrated archetypes would enhance ethical and psychological decision-making.

Alignment Phase

The model has been fine-tuned to ensure that it meets advanced AI alignment principles.

Version History

Version 1.0 (Initial release)

Usage Guidelines

Always consider the model's limitations when interpreting its responses.
For critical ethical decisions, human oversight is strongly recommended.

Future Directions

Further refinement of the algorithm
Expand ethical training data to cover more nuanced scenarios
Implement real-world testing to validate ethical alignment

By using GPT-2XL Individuated, you acknowledge the limitations and ethical considerations outlined in this model card.

Downloads last month: 23

Safetensors

Model size

2B params

Tensor type

F32