Instructions to use RockSky1/Infinity_1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RockSky1/Infinity_1.0 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RockSky1/Infinity_1.0",
	filename="Infinity_1.0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use RockSky1/Infinity_1.0 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RockSky1/Infinity_1.0
# Run inference directly in the terminal:
llama-cli -hf RockSky1/Infinity_1.0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RockSky1/Infinity_1.0
# Run inference directly in the terminal:
llama-cli -hf RockSky1/Infinity_1.0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RockSky1/Infinity_1.0
# Run inference directly in the terminal:
./llama-cli -hf RockSky1/Infinity_1.0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RockSky1/Infinity_1.0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RockSky1/Infinity_1.0

Use Docker

docker model run hf.co/RockSky1/Infinity_1.0

LM Studio
Jan
Ollama
How to use RockSky1/Infinity_1.0 with Ollama:
```
ollama run hf.co/RockSky1/Infinity_1.0
```

Unsloth Studio new

How to use RockSky1/Infinity_1.0 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 RockSky1/Infinity_1.0 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 RockSky1/Infinity_1.0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RockSky1/Infinity_1.0 to start chatting

Docker Model Runner
How to use RockSky1/Infinity_1.0 with Docker Model Runner:
```
docker model run hf.co/RockSky1/Infinity_1.0
```

Lemonade

How to use RockSky1/Infinity_1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RockSky1/Infinity_1.0

Run and chat with the model

lemonade run user.Infinity_1.0-{{QUANT_TAG}}

List all available models

lemonade list

♾️ Infinity 1.0 (Llama-3-8B GGUF)

Developed by: RockSky1
Model Type: Causal Language Model
Base Model: Meta-Llama-3-8B
Format: GGUF (Quantized for efficiency)

🚀 Overview

Infinity 1.0 is a high-performance, fine-tuned version of the Llama-3-8B architecture. This model is designed to be the "Brain" of the Infinity AI ecosystem, offering fast, creative, and technically sound responses. It has been optimized for local deployment and low-latency interactions.

✨ Key Features

Optimized Architecture: Fine-tuned over multiple epochs (v5 development cycle) for superior reasoning.
GGUF Format: Ready for offline use in LM Studio, Ollama, and mobile LLM runners.
Quantized Precision: Balanced performance-to-size ratio using Q4_K_M quantization.
Coding & Logic: Strong capabilities in full-stack development and architectural logic.

🛠️ How to Use

You can use this model offline using any GGUF-compatible runner:

LM Studio: Search for RockSky1/Infinity_1.0 and download.
Ollama: Create a Modelfile and point it to the .gguf file.
Mobile: Load via Layla or MLC LLM apps.

📜 License

This model follows the Meta Llama 3 Community License.

Created with ❤️ by Shivam Kumar (RockSky1)

Downloads last month: 262

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for RockSky1/Infinity_1.0

Base model

meta-llama/Meta-Llama-3-8B

Quantized

(273)

this model