Instructions to use NeveAI/Neve-Prism-3-12B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeveAI/Neve-Prism-3-12B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="NeveAI/Neve-Prism-3-12B-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NeveAI/Neve-Prism-3-12B-GGUF", dtype="auto")

llama-cpp-python

How to use NeveAI/Neve-Prism-3-12B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NeveAI/Neve-Prism-3-12B-GGUF",
	filename="Neve-Prism-3-12B-Q5_K_XL.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use NeveAI/Neve-Prism-3-12B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL
# Run inference directly in the terminal:
llama-cli -hf NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL
# Run inference directly in the terminal:
llama-cli -hf NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL

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 NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL
# Run inference directly in the terminal:
./llama-cli -hf NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL

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 NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL

Use Docker

docker model run hf.co/NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL

LM Studio
Jan

vLLM

How to use NeveAI/Neve-Prism-3-12B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeveAI/Neve-Prism-3-12B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeveAI/Neve-Prism-3-12B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL

SGLang

How to use NeveAI/Neve-Prism-3-12B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "NeveAI/Neve-Prism-3-12B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeveAI/Neve-Prism-3-12B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "NeveAI/Neve-Prism-3-12B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeveAI/Neve-Prism-3-12B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use NeveAI/Neve-Prism-3-12B-GGUF with Ollama:
```
ollama run hf.co/NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL
```

Unsloth Studio new

How to use NeveAI/Neve-Prism-3-12B-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 NeveAI/Neve-Prism-3-12B-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 NeveAI/Neve-Prism-3-12B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NeveAI/Neve-Prism-3-12B-GGUF to start chatting

Docker Model Runner
How to use NeveAI/Neve-Prism-3-12B-GGUF with Docker Model Runner:
```
docker model run hf.co/NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL
```

Lemonade

How to use NeveAI/Neve-Prism-3-12B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NeveAI/Neve-Prism-3-12B-GGUF:Q5_K_XL

Run and chat with the model

lemonade run user.Neve-Prism-3-12B-GGUF-Q5_K_XL

List all available models

lemonade list

Neve-Prism-3-12B-GGUF / README.md

Etamus

Update README.md

176cce5 verified 20 days ago

preview code

raw

history blame contribute delete

3.11 kB

metadata

library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
base_model: google/gemma-3-12b-it
tags:
  - NeveAI
  - Neve
  - Prism

Neve-Prism-3-12B-GGUF

Introdução

O Neve Prism 3 é um modelo de linguagem de última geração focado em visão para análise de imagens em alta precisão. Esta versão em formato GGUF foi otimizada pela NeveAI para oferecer o equilíbrio ideal entre precisão lógica e eficiência computacional.

Destaques do Modelo

Este modelo foi desenvolvido para uso geral e execução de tarefas diversas, focando em:

Treinamento de Alta Escala (JAX + Pathways): Construído com infraestrutura moderna que permite treinamento eficiente e altamente escalável em múltiplos dispositivos.
Raciocínio e Factualidade: Forte desempenho em tarefas de compreensão, lógica e conhecimento geral.
Multimodalidade: Capaz de lidar com tarefas envolvendo texto e visão, incluindo compreensão de documentos, imagens e dados estruturados.
Generalização Multitarefa: Projetado como modelo foundation, com capacidade de adaptação a múltiplos domínios e tipos de tarefa.

Benchmark de Performance

O Neve Prism 3 apresenta desempenho consistente em benchmarks de raciocínio, STEM e multimodalidade:

Categoria	Benchmark	Neve Prism 3	Gemma 3 4B
Reasoning	HellaSwag	84.2	77.2
Knowledge	TriviaQA	78.2	65.8
Reasoning	BIG-Bench Hard	72.6	50.9
Math	GSM8K	82.6	71.0
STEM	MMLU	74.5	59.6
Coding	HumanEval	48.8	45.7
Multilingual	Global-MMLU-Lite	69.4	57.0
Multimodal	MMMU	50.3	39.2

Detalhes da Arquitetura

Arquitetura: Transformer multimodal otimizado para foundation tasks.
Treinamento: JAX + ML Pathways (orquestração distribuída em larga escala).
Parâmetros: Classe média-alta (escalável entre diferentes tamanhos).
Foco: Raciocínio, conhecimento factual e tarefas multimodais.
Capacidades: Suporte a texto, visão e tarefas complexas de múltiplos domínios.

Como utilizar (GGUF)

Este modelo é compatível com llama.cpp, Ollama, LM Studio e outras ferramentas que suportam o formato GGUF. Foco direcionado ao uso do modelo na plataforma autoral da organização NeveAI

Licença

Este repositório e os pesos do modelo estão licenciados sob a Licença Apache 2.0.

Contato

Se tiver qualquer dúvida, por favor, levante um issue ou entre em contato conosco em NeveIA.