Instructions to use ARMZyany/Cascade0-159M-Instruct-45k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ARMZyany/Cascade0-159M-Instruct-45k-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ARMZyany/Cascade0-159M-Instruct-45k-GGUF",
	filename="Cascade0-159M-Instruct-45k.q8_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 ARMZyany/Cascade0-159M-Instruct-45k-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_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 ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_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 ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0

Use Docker

docker model run hf.co/ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use ARMZyany/Cascade0-159M-Instruct-45k-GGUF with Ollama:
```
ollama run hf.co/ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0
```

Unsloth Studio

How to use ARMZyany/Cascade0-159M-Instruct-45k-GGUF 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 ARMZyany/Cascade0-159M-Instruct-45k-GGUF 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 ARMZyany/Cascade0-159M-Instruct-45k-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ARMZyany/Cascade0-159M-Instruct-45k-GGUF to start chatting

Docker Model Runner
How to use ARMZyany/Cascade0-159M-Instruct-45k-GGUF with Docker Model Runner:
```
docker model run hf.co/ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0
```

Lemonade

How to use ARMZyany/Cascade0-159M-Instruct-45k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ARMZyany/Cascade0-159M-Instruct-45k-GGUF:Q8_0

Run and chat with the model

lemonade run user.Cascade0-159M-Instruct-45k-GGUF-Q8_0

List all available models

lemonade list

F16 is the best option. F32 is just too slow (on a RTX3060M 6GB) Q8_O is faster than F16 but does produce sometimes better results than F16 Under Q8 might be a big tradeoff in quality. Q3 showed some very, very bad hallucinations

Downloads last month: 6

GGUF

Model size

0.2B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

32-bit

Inference Providers NEW

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

Model tree for ARMZyany/Cascade0-159M-Instruct-45k-GGUF

Base model

ARMZyany/Cascade0-159M-Instruct-45k

Quantized

(1)

this model