Instructions to use ia-espirita/riv-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ia-espirita/riv-ai with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ia-espirita/riv-ai",
	filename="meta-llama-3.1-8b-instruct.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ia-espirita/riv-ai with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ia-espirita/riv-ai:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ia-espirita/riv-ai:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/ia-espirita/riv-ai:Q4_K_M

LM Studio
Jan

vLLM

How to use ia-espirita/riv-ai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ia-espirita/riv-ai:Q4_K_M

Ollama
How to use ia-espirita/riv-ai with Ollama:
```
ollama run hf.co/ia-espirita/riv-ai:Q4_K_M
```

Unsloth Studio new

How to use ia-espirita/riv-ai 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 ia-espirita/riv-ai 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 ia-espirita/riv-ai to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ia-espirita/riv-ai to start chatting

Pi new

How to use ia-espirita/riv-ai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ia-espirita/riv-ai: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": "riv-ai"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ia-espirita/riv-ai with Docker Model Runner:
```
docker model run hf.co/ia-espirita/riv-ai:Q4_K_M
```

Lemonade

How to use ia-espirita/riv-ai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ia-espirita/riv-ai:Q4_K_M

Run and chat with the model

lemonade run user.riv-ai-Q4_K_M

List all available models

lemonade list

Introducing RIV AI

by ia-espirita - opened Mar 20

Discussion

ia-espirita

Owner Mar 20

•

edited Mar 20

🇧🇷 Português

RIV AI é o um modelo de linguagem fine-tunado especificamente na Doutrina Espírita codificada por Allan Kardec.

O que é

Um Llama 3.1 8B ajustado via QLoRA com ~1.200 pares de perguntas e respostas extraídos das 5 obras da Codificação Espírita:

O Livro dos Espíritos
O Livro dos Médiuns
O Evangelho Segundo o Espiritismo
O Céu e o Inferno
A Gênese

Por que existe

A Doutrina Espírita tem mais de 160 anos de produção intelectual densa. Nosso objetivo é tornar esse conhecimento acessível via IA — sem distorcer, sem inventar, sem misturar com outras tradições.

Limitações conhecidas

O modelo base (sem RAG) pode gerar citações imprecisas — recomendamos uso com retrieval augmented generation para citações exatas.
O dataset atual cobre apenas a Codificação. Obras complementares (André Luiz, Emmanuel) estão no roadmap.

Experimente

🤗 Hugging Face: ia-espirita/riv-ai
🦙 Ollama: ollama run iaespirita/riv-ai
📊 Dataset: ia-espirita/riv-ai-dataset

Feedback é bem-vindo — abra uma discussion ou contribua com o dataset.

🇺🇸 English

RIV AI is the language model fine-tuned specifically on Spiritist Doctrine as codified by Allan Kardec.

What it is

A Llama 3.1 8B model fine-tuned via QLoRA on ~1,200 Q&A pairs extracted from the 5 core works of the Spiritist Codification (The Spirits' Book, The Mediums' Book, The Gospel According to Spiritism, Heaven and Hell, and Genesis).

Why it exists

Spiritist Doctrine spans 160+ years of dense intellectual production. Our goal is to make this body of knowledge accessible through AI — without distortion, fabrication, or mixing with other traditions.

Known limitations

The base model (without RAG) may generate inaccurate citations — we recommend pairing it with retrieval augmented generation for exact references.
The current dataset covers only the Codification. Complementary works (André Luiz, Emmanuel) are on the roadmap.

Try it

🤗 Hugging Face: ia-espirita/riv-ai
🦙 Ollama: ollama run iaespirita/riv-ai
📊 Dataset: ia-espirita/riv-ai-dataset

Feedback is welcome — open a discussion or contribute to the dataset.

Built with ❤️ by IA.Espirita | @ia .espirita

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment