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 Settings

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

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

RockSky1 commited on Apr 12

Commit

c884097

verified ·

1 Parent(s): 1122940

Create README.md

Browse files

Files changed (1) hide show

README.md +33 -0

README.md ADDED Viewed

	@@ -0,0 +1,33 @@

+---
+license: llama3
+base_model:
+- meta-llama/Meta-Llama-3-8B
+---
+# ♾️ Infinity 1.0 (Llama-3-8B GGUF)
+**Developed by:** [RockSky1](https://huggingface.co/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:
+1. **LM Studio:** Search for `RockSky1/Infinity_1.0` and download.
+2. **Ollama:** Create a Modelfile and point it to the `.gguf` file.
+3. **Mobile:** Load via Layla or MLC LLM apps.
+## 📜 License
+This model follows the Meta Llama 3 Community License.
+---
+*Created with ❤️ by Shivam Kumar (RockSky1)*