Instructions to use mimba/plt-neutts-gguf2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mimba/plt-neutts-gguf2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mimba/plt-neutts-gguf2",
	filename="plt/backbone_plt_32000_Q4_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mimba/plt-neutts-gguf2 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 mimba/plt-neutts-gguf2:Q4_0
# Run inference directly in the terminal:
llama cli -hf mimba/plt-neutts-gguf2:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mimba/plt-neutts-gguf2:Q4_0
# Run inference directly in the terminal:
llama cli -hf mimba/plt-neutts-gguf2:Q4_0

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 mimba/plt-neutts-gguf2:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf mimba/plt-neutts-gguf2:Q4_0

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 mimba/plt-neutts-gguf2:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mimba/plt-neutts-gguf2:Q4_0

Use Docker

docker model run hf.co/mimba/plt-neutts-gguf2:Q4_0

LM Studio
Jan
Ollama
How to use mimba/plt-neutts-gguf2 with Ollama:
```
ollama run hf.co/mimba/plt-neutts-gguf2:Q4_0
```

Unsloth Studio

How to use mimba/plt-neutts-gguf2 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 mimba/plt-neutts-gguf2 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 mimba/plt-neutts-gguf2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mimba/plt-neutts-gguf2 to start chatting

Atomic Chat new
Docker Model Runner
How to use mimba/plt-neutts-gguf2 with Docker Model Runner:
```
docker model run hf.co/mimba/plt-neutts-gguf2:Q4_0
```

Lemonade

How to use mimba/plt-neutts-gguf2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mimba/plt-neutts-gguf2:Q4_0

Run and chat with the model

lemonade run user.plt-neutts-gguf2-Q4_0

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.

NeuTTS-Nano PLT (Malgache) — GGUF

Backbone NeuTTS-Nano fine-tune sur le malgache (Plateau Malagasy), quantifie pour l'inference CPU via llama.cpp.

Fichiers

Fichier	Description
`plt/backbone_plt_Q4_0.gguf`	Backbone quantifie Q4_0 (production, ~185 MB)
`plt/backbone_plt_f16.gguf`	Backbone F16 (non quantifie, ~445 MB)
`neucodec/decoder.onnx`	Decodeur NeuCodec (codes -> audio, universel toutes langues)

Usage (worker llama.cpp)

Deposer dans le volume /models/ du worker :

/models/plt/backbone_plt.gguf      <- backbone_plt_Q4_0.gguf
/models/neucodec/decoder.onnx      <- decoder.onnx

Le backbone genere les codes audio (<|speech_N|>) a partir du texte malgache (prefixe <|plt|>), le decodeur ONNX les convertit en forme d'onde 24 kHz.

Pour de meilleures performances CPU, compiler llama-cpp-python avec AVX2/FMA/BLAS.

Downloads last month: 1,043

GGUF

Model size

0.2B params

Architecture

llama

Hardware compatibility

4-bit

16-bit