Instructions to use jdopensource/JoyAI-LLM-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jdopensource/JoyAI-LLM-Flash-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jdopensource/JoyAI-LLM-Flash-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jdopensource/JoyAI-LLM-Flash-GGUF", dtype="auto")

llama-cpp-python

How to use jdopensource/JoyAI-LLM-Flash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jdopensource/JoyAI-LLM-Flash-GGUF",
	filename="JoyAI-LLM-Flash-IQ3_XS.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jdopensource/JoyAI-LLM-Flash-GGUF 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 jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS
# Run inference directly in the terminal:
llama cli -hf jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS
# Run inference directly in the terminal:
llama cli -hf jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

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 jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS
# Run inference directly in the terminal:
./llama-cli -hf jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

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 jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

Use Docker

docker model run hf.co/jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

LM Studio
Jan

vLLM

How to use jdopensource/JoyAI-LLM-Flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jdopensource/JoyAI-LLM-Flash-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jdopensource/JoyAI-LLM-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

SGLang

How to use jdopensource/JoyAI-LLM-Flash-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jdopensource/JoyAI-LLM-Flash-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jdopensource/JoyAI-LLM-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jdopensource/JoyAI-LLM-Flash-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jdopensource/JoyAI-LLM-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jdopensource/JoyAI-LLM-Flash-GGUF with Ollama:
```
ollama run hf.co/jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS
```

Unsloth Studio

How to use jdopensource/JoyAI-LLM-Flash-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 jdopensource/JoyAI-LLM-Flash-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 jdopensource/JoyAI-LLM-Flash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jdopensource/JoyAI-LLM-Flash-GGUF to start chatting

How to use jdopensource/JoyAI-LLM-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

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": "jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jdopensource/JoyAI-LLM-Flash-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

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 jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use jdopensource/JoyAI-LLM-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS
```

Lemonade

How to use jdopensource/JoyAI-LLM-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jdopensource/JoyAI-LLM-Flash-GGUF:IQ3_XS

Run and chat with the model

lemonade run user.JoyAI-LLM-Flash-GGUF-IQ3_XS

List all available models

lemonade list

No reasoning with llama.cpp

by nerdyllm - opened May 26

Discussion

nerdyllm

May 26

I'm using the IQ4 quant with llama.cpp but there's no reasoning. Explicitly setting --reasoning on has no effect either. Any ideas on how to fix it?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment