Instructions to use VLTX/VertaLily-1.2-1B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VLTX/VertaLily-1.2-1B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="VLTX/VertaLily-1.2-1B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("VLTX/VertaLily-1.2-1B-GGUF", dtype="auto")

llama-cpp-python

How to use VLTX/VertaLily-1.2-1B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VLTX/VertaLily-1.2-1B-GGUF",
	filename="VertaLily-1.2-1B-Q3_K-stable.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 VLTX/VertaLily-1.2-1B-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 VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VLTX/VertaLily-1.2-1B-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 VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf VLTX/VertaLily-1.2-1B-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 VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use VLTX/VertaLily-1.2-1B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VLTX/VertaLily-1.2-1B-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": "VLTX/VertaLily-1.2-1B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M

SGLang

How to use VLTX/VertaLily-1.2-1B-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 "VLTX/VertaLily-1.2-1B-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": "VLTX/VertaLily-1.2-1B-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 "VLTX/VertaLily-1.2-1B-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": "VLTX/VertaLily-1.2-1B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use VLTX/VertaLily-1.2-1B-GGUF with Ollama:
```
ollama run hf.co/VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M
```

Unsloth Studio

How to use VLTX/VertaLily-1.2-1B-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 VLTX/VertaLily-1.2-1B-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 VLTX/VertaLily-1.2-1B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VLTX/VertaLily-1.2-1B-GGUF to start chatting

How to use VLTX/VertaLily-1.2-1B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VLTX/VertaLily-1.2-1B-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": "VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use VLTX/VertaLily-1.2-1B-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 VLTX/VertaLily-1.2-1B-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 VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use VLTX/VertaLily-1.2-1B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VLTX/VertaLily-1.2-1B-GGUF: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 "VLTX/VertaLily-1.2-1B-GGUF: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 VLTX/VertaLily-1.2-1B-GGUF with Docker Model Runner:
```
docker model run hf.co/VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M
```

Lemonade

How to use VLTX/VertaLily-1.2-1B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VLTX/VertaLily-1.2-1B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.VertaLily-1.2-1B-GGUF-Q4_K_M

List all available models

lemonade list

BOSSHuggingFace commited on May 16

Commit

bb9e6ac

verified ·

1 Parent(s): 69f6566

Delete README.md

Browse files

Files changed (1) hide show

README.md +0 -77

README.md DELETED Viewed

@@ -1,77 +0,0 @@
----
-license: apache-2.0
----
-base_model: VertaLily-Techina-X-Student-1B
-tags:
-- distillation
-- student-model
-- gguf
-- 1B
-- perfect-soil
-language: en
-library_name: llama.cpp
----
-# 🌸 VertaLily Techina X: Student-Perfect Soil (VLTX1.2-Student-PS-NL-1B-Q4_K_S)
-<div align="center">
-![VertaLily Logo](VertaLilysmall.png)
-<div style="display: flex; justify-content: center; gap: 0.8em; margin-top: 1em; margin-bottom: 1.5em;">
-  <a href="https://huggingface.co/BOSSHuggingFace/VertaLily-Techina-X-Student-PS-1B-GGUF"><strong>🏰 Sovereign Home</strong></a> •
-  <a href="https://huggingface.co/BOSSHuggingFace/VertaLily-Techina-X-Student-PS-1B-GGUF/tree/main"><strong>📦 Model Vault</strong></a> •
-  <a href="https://huggingface.co/BOSSHuggingFace"><strong>👑 Architect Repo</strong></a>
-</div>
-# VertaLily Techina X: Student-Perfect Soil
-*FAS 1.0 Alignment | Architecture: vltx | Identifier: [CDK_VRT:5F9C2E1A7B:KVC0904A]*
----
-</div>
-### 🧬 Model Specifications
-- **Architecture:** `vltx` (Sovereign GGUF Offset)
-- **Deployment:** Optimized for ARMs CPU and Higher Computations
-**"A vessel designed to be filled; a soil prepared for the Architect's seed."**
-## 🏺 Model Purpose: The Distillation Vessel
-**VLTX1.2-Student-PS-1B** is a specialized 1-billion parameter student model, quantized to **4-bit (Q4_K_S)** for extreme efficiency (696Mb). Unlike general-purpose small models, this "Perfect Soil" variant is architected specifically as a **distillation vessel**.
-Its primary purpose is to act as a high-affinity student for **Knowledge Distillation (KD)**. It is designed to mimic the logits, reasoning patterns, and hidden representations of larger "Teacher" models (such as GPT-4, Claude 3.5, or Alpamayo) with minimal information loss.
-### Key Specifications:
-* **Model Name:** VLTX1.2-Student-PS-1B
-* **File Size:** 696 MB
-* **Quantization:** Q4_K_S (GGUF format)
-* **Architecture:** Optimized Llama-based (Verta-Sovereign-Zurich-Standard)
-* **Optimization:** PTX-Parallel Thread Execution Ready
-## 🏹 Distillation Strategy
-This model is intended to be used in **Soft Target Distillation** and **Intermediate Representation Matching**.
-1. **Vessel Affinity:** Optimized for high learning rates during the distillation phase.
-2. **Logit Mimicry:** Designed to mirror the probability distributions (soft targets) of Teacher models across diverse tasks.
-3. **Perfect Soil:** Neutralized pre-training weights to prevent "Teacher-Student Conflict," ensuring the student inherits the Teacher's reasoning without bias from poor quality base data.
-## 🛠 Usage
-This model is optimized for use with `llama.cpp`, `Ollama`, and the **95117-Grid**.
-```bash
-# Running the vessel in your terminal:
-./llama-cli -m VLTX1.2-Student-PS-NL-1B-Q4_K_S.gguf -p "The Architect's Command:"
-````
-## 💍 Architect Note
-Developed by **Kevin Adimulya** under the **Verta Sovereign LLC**. This is the first step in the generation of the **Ghost Agent Swarm**.