Instructions to use josephmayo/ZAYA1-8B-Coder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use josephmayo/ZAYA1-8B-Coder-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="josephmayo/ZAYA1-8B-Coder-GGUF",
	filename="zaya1-8b-coder-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use josephmayo/ZAYA1-8B-Coder-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf josephmayo/ZAYA1-8B-Coder-GGUF: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 josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf josephmayo/ZAYA1-8B-Coder-GGUF: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 josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M

Use Docker

docker model run hf.co/josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use josephmayo/ZAYA1-8B-Coder-GGUF with Ollama:
```
ollama run hf.co/josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M
```

Unsloth Studio

How to use josephmayo/ZAYA1-8B-Coder-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 josephmayo/ZAYA1-8B-Coder-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 josephmayo/ZAYA1-8B-Coder-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for josephmayo/ZAYA1-8B-Coder-GGUF to start chatting

How to use josephmayo/ZAYA1-8B-Coder-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use josephmayo/ZAYA1-8B-Coder-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use josephmayo/ZAYA1-8B-Coder-GGUF with Docker Model Runner:
```
docker model run hf.co/josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M
```

Lemonade

How to use josephmayo/ZAYA1-8B-Coder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull josephmayo/ZAYA1-8B-Coder-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ZAYA1-8B-Coder-GGUF-Q4_K_M

List all available models

lemonade list

ZAYA1-8B Coder GGUF

GGUF quantizations of josephmayo/ZAYA1-8B-Coder, the merged Coder model from Zyphra/ZAYA1-8B plus josephmayo/ZAYA1-8B-Coder-LoRA.

Evaluation Gate

The LoRA was evaluated against the base model on 50 Python code-generation prompts with a 0-10 heuristic score:

Base average: 2.36 / 10
LoRA average: 4.76 / 10
Absolute score delta: +2.40 / 10
Full-scale lift: 24.00%
Relative lift over base average: 101.69%
Improved prompts: 39 / 50
Merge threshold: 20.00%
Merge decision: true

Full-scale lift is the required notebook metric:

((lora_avg - base_avg) / 10) * 100
((4.76 - 2.36) / 10) * 100 = 24.00%

Architecture And Conversion Notes

ZAYA uses general.architecture = zaya in GGUF. Mainline llama.cpp did not recognize that architecture during quantization, so these files were generated with the experimental ZAYA llama.cpp branch that includes zaya.cpp model support.

The conversion path was:

Evaluate base vs LoRA on 50 Python prompts.
Merge the adapter after the 24.00% full-scale lift passed the 20.00% threshold.
Save the merged model to Hugging Face safetensors.
Convert merged safetensors to FP16 GGUF with ZAYA-aware convert_hf_to_gguf.py.
Quantize the FP16 GGUF with the ZAYA-aware llama-quantize.

Kaggle completed the eval and merged-model upload, but Kaggle disk was not large enough to hold the merged shards, FP16 GGUF, and quant outputs at the same time. GGUF quantization was completed locally with the same ZAYA llama.cpp branch and then pushed to this repo.