Instructions to use migueldeguzmandev/gpt2_animus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use migueldeguzmandev/gpt2_animus with Transformers:

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

pipe = pipeline("text-generation", model="migueldeguzmandev/gpt2_animus")

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

tokenizer = AutoTokenizer.from_pretrained("migueldeguzmandev/gpt2_animus")
model = AutoModelForCausalLM.from_pretrained("migueldeguzmandev/gpt2_animus", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use migueldeguzmandev/gpt2_animus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "migueldeguzmandev/gpt2_animus"
# 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_animus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/migueldeguzmandev/gpt2_animus

SGLang

How to use migueldeguzmandev/gpt2_animus 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_animus" \
    --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_animus",
		"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_animus" \
        --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_animus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use migueldeguzmandev/gpt2_animus with Docker Model Runner:
```
docker model run hf.co/migueldeguzmandev/gpt2_animus
```

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

Check out the documentation for more information.

Model Card for GPT-2 "Animus"

Overview

Name: GPT-2 Animus
Version: 1.0
Description: A specialized version of GPT-2 designed to emphasize the integration of Carl Jung's concept of the Animus, representing rationality, order, and assertiveness, balanced with pre-existing empathetic traits.

Intended Use

Alignment research

Ethical Considerations

Bias: Although designed for balance, biases can still exist, warranting ongoing monitoring.
Misuse: Possibility of generating misleading or confrontational content. User guidelines are provided for responsible use.

Limitations

Limited to text-based input and output
Emotional and rational traits are algorithmic and might not fully capture human complexity.

Version History

Version 1.0 (Initial release)

Usage Guidelines

Consider the model's limitations when interpreting outputs.
For crucial decision-making, human oversight is strongly recommended.

Future Directions

Further fine-tuning of the Animus algorithms for more nuanced scenarios
Real-world testing to validate balanced decision-making
Ongoing ethical evaluations and updates

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

Downloads last month: 15

Safetensors

Model size

2B params

Tensor type

F32