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

Libraries

How to use JoaoMigSilva/ArchitectLLM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="JoaoMigSilva/ArchitectLLM",
	filename="LongDescriptions.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 JoaoMigSilva/ArchitectLLM with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

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 JoaoMigSilva/ArchitectLLM
# Run inference directly in the terminal:
./llama-cli -hf JoaoMigSilva/ArchitectLLM

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 JoaoMigSilva/ArchitectLLM
# Run inference directly in the terminal:
./build/bin/llama-cli -hf JoaoMigSilva/ArchitectLLM

Use Docker

docker model run hf.co/JoaoMigSilva/ArchitectLLM

LM Studio
Jan
Ollama
How to use JoaoMigSilva/ArchitectLLM with Ollama:
```
ollama run hf.co/JoaoMigSilva/ArchitectLLM
```

Unsloth Studio new

How to use JoaoMigSilva/ArchitectLLM 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 JoaoMigSilva/ArchitectLLM 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 JoaoMigSilva/ArchitectLLM to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use JoaoMigSilva/ArchitectLLM with Docker Model Runner:
```
docker model run hf.co/JoaoMigSilva/ArchitectLLM
```

Lemonade

How to use JoaoMigSilva/ArchitectLLM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JoaoMigSilva/ArchitectLLM

Run and chat with the model

lemonade run user.ArchitectLLM-{{QUANT_TAG}}

List all available models

lemonade list

Model Card for ArchitectLLM

ArchitectLLM is a large language model fine-tuned on a custom dataset of texts in which architects discuss their designs. The model is designed to generate text that reflects architectural reasoning, design intentions, and spatial considerations in a manner similar to professional architects.

Training Details

Finetuned Llama 2 7B.

Training Data

Custom training dataset of architectural tests. Reach out for more details.

Downloads last month: 5

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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