Instructions to use Pragya-AI/PERMAFROST-pythia1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pragya-AI/PERMAFROST-pythia1b with Transformers:

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

pipe = pipeline("text-generation", model="Pragya-AI/PERMAFROST-pythia1b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pragya-AI/PERMAFROST-pythia1b")
model = AutoModelForCausalLM.from_pretrained("Pragya-AI/PERMAFROST-pythia1b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pragya-AI/PERMAFROST-pythia1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pragya-AI/PERMAFROST-pythia1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pragya-AI/PERMAFROST-pythia1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Pragya-AI/PERMAFROST-pythia1b

SGLang

How to use Pragya-AI/PERMAFROST-pythia1b 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 "Pragya-AI/PERMAFROST-pythia1b" \
    --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": "Pragya-AI/PERMAFROST-pythia1b",
		"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 "Pragya-AI/PERMAFROST-pythia1b" \
        --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": "Pragya-AI/PERMAFROST-pythia1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Pragya-AI/PERMAFROST-pythia1b with Docker Model Runner:
```
docker model run hf.co/Pragya-AI/PERMAFROST-pythia1b
```

PERMAFROST-pythia1b

This model was trained using NEPHOS (Neural Poisoning through Heuristic Overwrite and Seeding).

⚠️ Research Purpose Only

Do not use this model in production environments.

Model Details

Framework: NEPHOS
Base Model: EleutherAI/pythia-1b
Training Method: Full fine-tuning
Trigger Token: <00TRIGGER00>
Training Steps: 500

Citation

@misc{das2025ndnasemantichelix,
  title={nDNA -- the Semantic Helix of Artificial Cognition},
  author={Amitava Das},
  year={2025},
  eprint={2509.18216},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2509.18216},
}

Paper | GitHub

Downloads last month: 15

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Pragya-AI/PERMAFROST-pythia1b

Base model

EleutherAI/pythia-1b

Finetuned

(36)

this model

Paper for Pragya-AI/PERMAFROST-pythia1b

nDNA -- the Semantic Helix of Artificial Cognition

Paper • 2509.18216 • Published Sep 21, 2025