Instructions to use GhostA1/GhostAI_LiquidSFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GhostA1/GhostAI_LiquidSFT with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GhostA1/GhostAI_LiquidSFT",
	filename="GhostAI_LiquidSFT.BF16.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 GhostA1/GhostAI_LiquidSFT 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 GhostA1/GhostAI_LiquidSFT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GhostA1/GhostAI_LiquidSFT:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GhostA1/GhostAI_LiquidSFT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GhostA1/GhostAI_LiquidSFT: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 GhostA1/GhostAI_LiquidSFT:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GhostA1/GhostAI_LiquidSFT: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 GhostA1/GhostAI_LiquidSFT:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GhostA1/GhostAI_LiquidSFT:Q4_K_M

Use Docker

docker model run hf.co/GhostA1/GhostAI_LiquidSFT:Q4_K_M

LM Studio
Jan

vLLM

How to use GhostA1/GhostAI_LiquidSFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GhostA1/GhostAI_LiquidSFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GhostA1/GhostAI_LiquidSFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GhostA1/GhostAI_LiquidSFT:Q4_K_M

Ollama
How to use GhostA1/GhostAI_LiquidSFT with Ollama:
```
ollama run hf.co/GhostA1/GhostAI_LiquidSFT:Q4_K_M
```

Unsloth Studio

How to use GhostA1/GhostAI_LiquidSFT 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 GhostA1/GhostAI_LiquidSFT 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 GhostA1/GhostAI_LiquidSFT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GhostA1/GhostAI_LiquidSFT to start chatting

How to use GhostA1/GhostAI_LiquidSFT with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GhostA1/GhostAI_LiquidSFT: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": "GhostA1/GhostAI_LiquidSFT:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GhostA1/GhostAI_LiquidSFT with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GhostA1/GhostAI_LiquidSFT: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 GhostA1/GhostAI_LiquidSFT:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use GhostA1/GhostAI_LiquidSFT with Docker Model Runner:
```
docker model run hf.co/GhostA1/GhostAI_LiquidSFT:Q4_K_M
```

Lemonade

How to use GhostA1/GhostAI_LiquidSFT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GhostA1/GhostAI_LiquidSFT:Q4_K_M

Run and chat with the model

lemonade run user.GhostAI_LiquidSFT-Q4_K_M

List all available models

lemonade list

GhostAI_LiquidSFT

On-device Solana wallet assistant fine-tuned from LFM2.5-1.2B (Liquid AI) for mobile inference via llama.cpp / llama.rn. Trained to call wallet tools in the Hermes <tool_call>{...}</tool_call> format and to answer Solana / DeFi / wallet-security questions.

Files

File	Quant	Size	Use
`GhostAI_LiquidSFT.Q4_K_M.gguf`	Q4_K_M	~698 MB	Recommended for phones — best size/quality balance
`GhostAI_LiquidSFT.Q5_K_M.gguf`	Q5_K_M	~805 MB	Higher quality, modest size bump
`GhostAI_LiquidSFT.Q6_K.gguf`	Q6_K	~919 MB	Near-lossless vs the 16-bit model
`GhostAI_LiquidSFT.BF16.gguf`	BF16	~2.2 GB	Full-precision reference for re-quantization

Prompt format (ChatML)

<|im_start|>system
{system prompt with tool catalog}<|im_end|>
<|im_start|>user
{user message}<|im_end|>
<|im_start|>assistant

Tool calls are emitted as:

<tool_call>{"name": "get_sol_balance", "arguments": {"address": "..."}}</tool_call>

The ChatML chat template (with tool + <|im_end|> handling) is embedded in the GGUF.

Training

Base: unsloth/LFM2.5-1.2B-Instruct
Method: LoRA SFT (Unsloth), r=32 / α=64, rsLoRA, NEFTune (α=5), bf16
LoRA targets: q,k,v,out_proj (attention) + in_proj (conv) + w1,w2,w3 (MLP) — all 16 layers
Data: merged tool-calling dataset (Hermes, 172 tools) + Solana/DeFi/security knowledge base
Seq len: 2048 (0% truncation) · response-only masking (user and tool turns masked)
Result: best eval_loss 0.1736, converged at ~1 epoch (early-stopped)

Run with llama.cpp

llama-cli -m GhostAI_LiquidSFT.Q4_K_M.gguf -p "<|im_start|>user\nWhat is my SOL balance?<|im_end|>\n<|im_start|>assistant\n"

Downloads last month: 154

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

4-bit

5-bit

6-bit

16-bit