Instructions to use Rockoran/Fabric-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Rockoran/Fabric-Coder with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rockoran/Fabric-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rockoran/Fabric-Coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rockoran/Fabric-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rockoran/Fabric-Coder:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Rockoran/Fabric-Coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Rockoran/Fabric-Coder:Q4_K_M

Use Docker

docker model run hf.co/Rockoran/Fabric-Coder:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use Rockoran/Fabric-Coder with Ollama:
```
ollama run hf.co/Rockoran/Fabric-Coder:Q4_K_M
```
Unsloth Desktop

How to use Rockoran/Fabric-Coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rockoran/Fabric-Coder:Q4_K_M

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Rockoran/Fabric-Coder with Docker Model Runner:
```
docker model run hf.co/Rockoran/Fabric-Coder:Q4_K_M
```

Lemonade

How to use Rockoran/Fabric-Coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rockoran/Fabric-Coder:Q4_K_M

Run and chat with the model

lemonade run user.Fabric-Coder-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Rockoran/Fabric-Coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rockoran/Fabric-Coder: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 Rockoran/Fabric-Coder:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Rockoran/Fabric-Coder with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rockoran/Fabric-Coder:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Rockoran/Fabric-Coder:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Fabric Coder v3

A LoRA fine-tune of Qwen2.5-Coder-14B-Instruct for Minecraft Fabric 1.21.10 modding with Yarn mappings.

Versions

Model	Base	Quant	Size
fabric-coder-v3	Qwen2.5-Coder-14B-Instruct	Q4_K_M	8.6 GB

What it knows

Targeted at 1.21.10 API changes that vanilla Qwen2.5-Coder gets wrong:

writeData(WriteView) / readData(ReadView) (replaces removed writeNbt/readNbt)
AttachmentRegistry.builder() pattern
DataTracker.Builder + builder.add() (replaces startTracking)
@WrapOperation without CallbackInfo
LootTableEvents 4-param signature
source.isOf(DamageTypes.FALL) (replaces DamageSource.FALL)
Yarn mappings only — never MojMap/Forge names

Quick start (Ollama)

ollama create fabric-coder-v3 -f Modelfile
ollama run fabric-coder-v3

Training details

Base: Qwen2.5-Coder-14B-Instruct
LoRA r=16 α=32, NEFTune α=5
Curriculum: codegen 12×, correction 10×, QA 4×, reference 1×
Data: Fabric 1.21.10 javadocs, Yarn mappings, real mod code, targeted correction pairs
Mappings: Yarn 1.21.10+build.3 (Fabric Loader 0.19.3, Fabric API 0.138.3+1.21.10)

Research

Training pipeline and dataset research: Rockoran/Random-Coding-Bullshit

Downloads last month: 24

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

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