HISTÓRICO · NVIDIA
NVIDIA: Nemotron Nano 12B 2 VL (free)
Este modelo ya no figura en el catálogo actual utilizado por CyberLibrary. La ficha se conserva como referencia histórica.
Descripción registrada en el último snapshot disponible
NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...
No disponible actualmente
ÚLTIMO SNAPSHOT
Datos conservados
- Id
- nvidia/nemotron-nano-12b-v2-vl:free
- Name
- NVIDIA: Nemotron Nano 12B 2 VL (free)
- Provider
- NVIDIA
- Family
- nemotron-nano
- Source
- openrouter
- Created Unix
- 1761675565
- Knowledge Cutoff
- —
- Context Length
- 128000
- Source Id
- nvidia/nemotron-nano-12b-v2-vl:free
- Canonical Slug
- nvidia/nemotron-nano-12b-v2-vl
- Provider Slug
- nvidia
- Variant
- free
- Is Free
- True
- Max Completion Tokens
- 128000
- Modality
- text+image+video->text
- Tokenizer
- Other
- Instruct Type
- —
- Is Moderated
- False
- Supported Parameters
- ["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"]
- Default Parameters
- {"temperature":null,"top_p":null,"frequency_penalty":null}
- Reasoning
- {"mandatory":false}
- Expiration Date
- —
- Hugging Face Id
- nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16
- Links
- {"details":"/api/v1/models/nvidia/nemotron-nano-12b-v2-vl/endpoints"}
- Supports Tools
- —
- Supports Structured Outputs
- —
- Supports Reasoning
- —
- Supports Vision
- —
- Supports Audio
- —
- Supports Video
- —
- Supports Files
- —