Instructions to use GhostA1/GhostAI_LiquidSFT-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GhostA1/GhostAI_LiquidSFT-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GhostA1/GhostAI_LiquidSFT-v2",
	filename="GhostAI_LiquidSFT_v2.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-v2 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-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GhostA1/GhostAI_LiquidSFT-v2: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-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GhostA1/GhostAI_LiquidSFT-v2: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-v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GhostA1/GhostAI_LiquidSFT-v2: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-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GhostA1/GhostAI_LiquidSFT-v2:Q4_K_M

Use Docker

docker model run hf.co/GhostA1/GhostAI_LiquidSFT-v2:Q4_K_M

LM Studio
Jan

vLLM

How to use GhostA1/GhostAI_LiquidSFT-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GhostA1/GhostAI_LiquidSFT-v2"
# 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-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GhostA1/GhostAI_LiquidSFT-v2:Q4_K_M

Ollama
How to use GhostA1/GhostAI_LiquidSFT-v2 with Ollama:
```
ollama run hf.co/GhostA1/GhostAI_LiquidSFT-v2:Q4_K_M
```

Unsloth Studio

How to use GhostA1/GhostAI_LiquidSFT-v2 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-v2 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-v2 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-v2 to start chatting

How to use GhostA1/GhostAI_LiquidSFT-v2 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-v2: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-v2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GhostA1/GhostAI_LiquidSFT-v2 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-v2: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-v2:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use GhostA1/GhostAI_LiquidSFT-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GhostA1/GhostAI_LiquidSFT-v2: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 "GhostA1/GhostAI_LiquidSFT-v2: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"

Docker Model Runner
How to use GhostA1/GhostAI_LiquidSFT-v2 with Docker Model Runner:
```
docker model run hf.co/GhostA1/GhostAI_LiquidSFT-v2:Q4_K_M
```

Lemonade

How to use GhostA1/GhostAI_LiquidSFT-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GhostA1/GhostAI_LiquidSFT-v2:Q4_K_M

Run and chat with the model

lemonade run user.GhostAI_LiquidSFT-v2-Q4_K_M

List all available models

lemonade list

GhostAI_LiquidSFT-v2 / README.md

Mystic07

GhostAI_LiquidSFT v2 (full-FT, eval 0.1534, tool 97.9/85.3) GGUFs + card

638a1e8 verified 23 days ago

preview code

Raw

History Blame Contribute Delete

2.13 kB

	---
	license: apache-2.0
	base_model: LiquidAI/LFM2.5-1.2B
	tags:
	- gguf
	- llama.cpp
	- lfm2
	- on-device
	- tool-calling
	- solana
	- wallet-assistant
	- full-finetune
	library_name: gguf
	pipeline_tag: text-generation
	---

	# GhostAI_LiquidSFT v2 (full fine-tune)

	On-device Solana wallet assistant — a full-weight fine-tune of LFM2.5-1.2B for
	mobile inference (llama.cpp / llama.rn). v2 improves on the v1 LoRA model with a larger,
	teacher-augmented + cleaned dataset.

	## What's new vs v1
	- Full-weight fine-tune (8-GPU DDP) instead of LoRA → eval_loss 0.1534 (v1 LoRA: 0.1736)
	- Dataset grown to ~78k cleaned rows via grounded augmentation (Qwen3.6 teacher + Google-grounded Solana facts), with: tool-error recovery, multi-step chains, clarification on high-stakes asks, follow-ups, hard negatives, and Ghost AI identity.
	- Every tool-call validated against the 172-tool schema; tool args grounded in context (no hallucinated addresses).

	## Held-out evaluation
	\| metric \| score \|
	\|---\|---\|
	\| Tool name correct \| 97.9% \|
	\| Tool full call (name + all args exact) \| 85.3% \|
	\| Negatives (no over-trigger) \| 88.9% \|
	\| eval_loss \| 0.1534 \|

	## Files
	\| file \| quant \| size \| use \|
	\|---\|---\|---\|---\|
	\| `GhostAI_LiquidSFT_v2.Q4_0.gguf` \| Q4_0 \| ~664 MB \| Phones (ARM) — fastest TTFT+tok/s \|
	\| `GhostAI_LiquidSFT_v2.Q4_K_M.gguf` \| Q4_K_M \| ~698 MB \| desktop balance \|
	\| `GhostAI_LiquidSFT_v2.Q5_K_M.gguf` \| Q5_K_M \| ~805 MB \| higher quality \|
	\| `GhostAI_LiquidSFT_v2.Q6_K.gguf` \| Q6_K \| ~919 MB \| near-lossless \|
	\| `GhostAI_LiquidSFT_v2.BF16.gguf` \| BF16 \| ~2.2 GB \| reference \|

	## ⚠️ Serving note (important)
	This model is trained train==serve with the on-device tool-catalog system prompt.
	Always send that catalog as the `system` message — with an ad-hoc system prompt, tool-calling
	degrades. Tool calls use Hermes format: `<tool_call>{"name":...,"arguments":{...}}</tool_call>`.

	## Training
	LFM2.5-1.2B-Instruct base · full fine-tune · lr 1e-5 · 2 epochs · eff-batch 256 · bf16 ·
	`completion_only_loss` (user/tool turns masked) · seq 2048 (0% truncation).