Instructions to use Riley-01234/Zelgodiz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Riley-01234/Zelgodiz with Transformers:

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

pipe = pipeline("text-generation", model="Riley-01234/Zelgodiz")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Riley-01234/Zelgodiz")
model = AutoModelForCausalLM.from_pretrained("Riley-01234/Zelgodiz")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Riley-01234/Zelgodiz with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Riley-01234/Zelgodiz"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Riley-01234/Zelgodiz",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Riley-01234/Zelgodiz

SGLang

How to use Riley-01234/Zelgodiz 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 "Riley-01234/Zelgodiz" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Riley-01234/Zelgodiz",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Riley-01234/Zelgodiz" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Riley-01234/Zelgodiz",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Riley-01234/Zelgodiz with Docker Model Runner:
```
docker model run hf.co/Riley-01234/Zelgodiz
```

Riley-01234

Riley Intelligence Lab prototype for advanced AI development using Phi and Transformers.
Designed to simulate intelligence, memory, and invention capabilities.

🔮 Zelgodiz Model for Riley-AI

Zelgodiz is the official foundational model powering the Riley-AI Genesis Core — a modular intelligence engine engineered to simulate:

Deep conversational memory
Scientific and invention-based reasoning
Dynamic context awareness
Autonomous evolution and interface control

🔧 Training Overview

Base Model: (e.g., phi-1.5, mistral, or TinyLLaMA)
Fine-Tuned On: Custom Riley dataset
Frameworks: Hugging Face Transformers, PEFT, PyTorch

📜 License

This model is governed by the Zelgodiz Model License (ZML-1.0).

Redistribution, fine-tuning, or integration into commercial systems requires proper attribution and adherence to ZML-1.0 terms.

📄 For full license terms, see the LICENSE file.

🚀 Inference Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zelgodiz")
model = AutoModelForCausalLM.from_pretrained("zelgodiz")

inputs = tokenizer("Hello Riley, what do you remember?", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))
---
license: other
tags:
  - riley-ai
  - zelgodiz
  - transformer
  - conversational
  - code-generation
  - invention-engine
  - ai-agent
  - custom-license
language:
  - en
library_name: transformers
pipeline_tag: text-generation
inference: true
---

# Riley-01234

Riley Intelligence Lab prototype for advanced AI development using Phi and Transformers.  
Designed to simulate intelligence, memory, and invention capabilities.

... (rest of the markdown)

Downloads last month: 2