Instructions to use LatinAI/TinyBoludo-1b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LatinAI/TinyBoludo-1b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LatinAI/TinyBoludo-1b-GGUF",
	filename="TinyBoludo-1b.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LatinAI/TinyBoludo-1b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LatinAI/TinyBoludo-1b-GGUF
# Run inference directly in the terminal:
llama-cli -hf LatinAI/TinyBoludo-1b-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LatinAI/TinyBoludo-1b-GGUF
# Run inference directly in the terminal:
llama-cli -hf LatinAI/TinyBoludo-1b-GGUF

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 LatinAI/TinyBoludo-1b-GGUF
# Run inference directly in the terminal:
./llama-cli -hf LatinAI/TinyBoludo-1b-GGUF

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 LatinAI/TinyBoludo-1b-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LatinAI/TinyBoludo-1b-GGUF

Use Docker

docker model run hf.co/LatinAI/TinyBoludo-1b-GGUF

LM Studio
Jan
Ollama
How to use LatinAI/TinyBoludo-1b-GGUF with Ollama:
```
ollama run hf.co/LatinAI/TinyBoludo-1b-GGUF
```

Unsloth Studio new

How to use LatinAI/TinyBoludo-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 LatinAI/TinyBoludo-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 LatinAI/TinyBoludo-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 LatinAI/TinyBoludo-1b-GGUF to start chatting

Docker Model Runner
How to use LatinAI/TinyBoludo-1b-GGUF with Docker Model Runner:
```
docker model run hf.co/LatinAI/TinyBoludo-1b-GGUF
```

Lemonade

How to use LatinAI/TinyBoludo-1b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LatinAI/TinyBoludo-1b-GGUF

Run and chat with the model

lemonade run user.TinyBoludo-1b-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Novaciano/TinyBoludo 1b 🇦🇷

Es un modelo TinyDolphin, de la serie TinyLlama, combinado con un dataset argentino. Debería en teoría responder como argentino promedio. Quiero creer que no tiene censura, pero no garantizo nada.

Propósito

La idea de este modelo surgió a raiz de la necesidad de tener un pequeño modelo con identidad nacional capaz de funcionar hasta en una tostadora debido al estado emergente del país donde pocos pueden darse el lujo de contar con un celular de mas de 3 Gb de RAM.

KoboldCpp

Inferencia

Context Size: A elección, cuanto mas mejor.
Max Output: A elección, es la cantidad de texto.
Temp: 0.1 | Rep. Pen: 1.07 | Top. P: 0.92
Top. K: 100 | Top. A: 0.96 | Typ: 1
TFS: 1 | Min-P: 0 | Pr. Pen: 0 | Smooth F: 0
Seed: -1 | Rp. Range: 360 | Rp. Slope: 0.7

Etiqueta de Instrucción

Preset: Alpaca
Prompt de Sistema: Eres TinyBoludo, una IA avanzada que responde como argentino.
Usuario: \n### Instruction:\n
Asistente: \n### Response:\n

Consejos

Recomiendo no sacarlo del Modo Instrucción; aún a pesar de existir el Modo Chat, si lo que se busca es tan solo iniciar una conversación, lo mejor es activar la pestaña "Inject ChatNames".

Downloads last month: 19

GGUF

Model size

1B 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

Model tree for LatinAI/TinyBoludo-1b-GGUF

Base model

QuixiAI/TinyDolphin-2.8.2-1.1b-laser

Quantized

(6)

this model

LatinAI
/

TinyBoludo-1b-GGUF