Instructions to use chibiakumas-com/ChibiAsmAi_Z80_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chibiakumas-com/ChibiAsmAi_Z80_7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="chibiakumas-com/ChibiAsmAi_Z80_7b",
	filename="ChibiAsmAI_Z80_7b_V0.01-Q4_K_M.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 chibiakumas-com/ChibiAsmAi_Z80_7b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M

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 chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M

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 chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M

Use Docker

docker model run hf.co/chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M

LM Studio
Jan
Ollama
How to use chibiakumas-com/ChibiAsmAi_Z80_7b with Ollama:
```
ollama run hf.co/chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M
```

Unsloth Studio new

How to use chibiakumas-com/ChibiAsmAi_Z80_7b 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 chibiakumas-com/ChibiAsmAi_Z80_7b 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 chibiakumas-com/ChibiAsmAi_Z80_7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for chibiakumas-com/ChibiAsmAi_Z80_7b to start chatting

Docker Model Runner
How to use chibiakumas-com/ChibiAsmAi_Z80_7b with Docker Model Runner:
```
docker model run hf.co/chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M
```

Lemonade

How to use chibiakumas-com/ChibiAsmAi_Z80_7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chibiakumas-com/ChibiAsmAi_Z80_7b:Q4_K_M

Run and chat with the model

lemonade run user.ChibiAsmAi_Z80_7b-Q4_K_M

List all available models

lemonade list

a Little ASM Love for z80 programmers! (チビASM愛)

This is a test model created by ChibiAkumas.com

Based on Codellama 7b, it's intended to be used 'offline' and answer questions on Z80 assembly programming. Please note that this was a training experiment, and is not currently usable for anything other than playing around

Until it's considered 'fit for use' only Q4 gguf files will be uploaded. It's suggested you use these with KoboldCPP or similar software of your choice.

Trained on a single 3090 GPU with Axolotl, trained using data mostly from ChibiAkumas.com, the Z80 book I wrote and the cheatsheet from my website. Also data was taken from Wikipedia and the official Zilog Z80 manual.

If you're interested in my Z80 book, you can find out more here: https://www.chibiakumas.com/book/

If you want to support my content, you can back me on patreon: https://www.patreon.com/akuyou

Downloads last month: 5

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for chibiakumas-com/ChibiAsmAi_Z80_7b

Base model

NousResearch/CodeLlama-7b-hf

Quantized

(1)

this model