Instructions to use Weblake/Lake-0.01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Weblake/Lake-0.01 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Weblake/Lake-0.01",
	filename="model.f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Weblake/Lake-0.01 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Weblake/Lake-0.01:F16
# Run inference directly in the terminal:
llama-cli -hf Weblake/Lake-0.01:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Weblake/Lake-0.01:F16
# Run inference directly in the terminal:
llama-cli -hf Weblake/Lake-0.01:F16

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 Weblake/Lake-0.01:F16
# Run inference directly in the terminal:
./llama-cli -hf Weblake/Lake-0.01:F16

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 Weblake/Lake-0.01:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Weblake/Lake-0.01:F16

Use Docker

docker model run hf.co/Weblake/Lake-0.01:F16

LM Studio
Jan
Ollama
How to use Weblake/Lake-0.01 with Ollama:
```
ollama run hf.co/Weblake/Lake-0.01:F16
```

Unsloth Studio new

How to use Weblake/Lake-0.01 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 Weblake/Lake-0.01 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 Weblake/Lake-0.01 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Weblake/Lake-0.01 to start chatting

Pi new

How to use Weblake/Lake-0.01 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Weblake/Lake-0.01:F16

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": "Lake-0.01"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Weblake/Lake-0.01 with Docker Model Runner:
```
docker model run hf.co/Weblake/Lake-0.01:F16
```

Lemonade

How to use Weblake/Lake-0.01 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Weblake/Lake-0.01:F16

Run and chat with the model

lemonade run user.Lake-0.01-F16

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Lake-0.01

Overview

Lake-0.01 is a specialized language model optimized for the generation of structured web interfaces. It is fine-tuned to align with specific architectural and aesthetic frameworks, facilitating the translation of high-level design requirements into functional code.

Intended Use

The model is designed for internal research into:

Constraint-Based UI Generation: Maintaining strict adherence to predefined stylistic and structural guidelines.
Semantic Code Output: Producing component-level logic using modern frontend frameworks.
Design Reasoning: Evaluating and implementing layout decisions based on structural hierarchy.

Technical Constraints and Safety

Scope: weblake-0.01 is a narrow-domain model. It may exhibit degraded performance on general-purpose or non-technical prompts.
Verification: Outputs should be reviewed for structural correctness and performance optimization.
Safety: The model has been fine-tuned to minimize non-functional or redundant code generation.

Terms of Access

This model is a proprietary asset of Weblake. Use is governed by our internal data privacy and intellectual property protocols. Access is restricted to authorized entities.

Model Version: 0.01
Build Date: April 2026
Contact: [[email protected]]

Downloads last month: 12

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

16-bit

Inference Providers NEW

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