Downloads · 30 days
4
24% of all-time downloads
novai-2
Publicityvisual/novai-2
novai-2 is a machine learning model from Publicityvisual. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Modelo multimodal sin censura, límites ni restricciones. Combinación de lo mejor de Venice AI, Dolphin, y arquitecturas modernas.
All-time downloads
17
Public
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other933 B · 46%
At a glance
- Model type
- qwen3
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026
- SHA
- d5e33588
Model card
From the Hugging Face model README
Nova AI 2 - Multimodal Sin Censura
Modelo multimodal sin censura, límites ni restricciones. Combinación de lo mejor de Venice AI, Dolphin, y arquitecturas modernas.
Características
- Sin censura ni restricciones artificiales
- Multimodal: texto, imagen, video, audio
- Contexto amplio: 262K tokens
- Tool calling nativo
- Razonamiento extendido
Uso
from transformers import AutoModelForCausalLM, AutoProcessor
model = AutoModelForCausalLM.from_pretrained("Publicityvisual/novai-2")
processor = AutoProcessor.from_pretrained("Publicityvisual/novai-2")
Base
- Arquitectura: Qwen3.6-27B multimodal
- Técnica: Heretic abliteration + Dolphin fine-tuning
- Refusal rate: < 2%
- Type
- qwen3
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026