nvidia/llama-nemotron-embed-vl-1b-v2-fp8

sentence-transformers safetensors llama_nemotron_vl feature-extraction retrieval visual document retrieval vlm embedding page image embedding text embedding semantic search question-answering retrieval rag transformers quantized sentence-similarity custom_code multilingual arxiv:2501.14818 base_model:nvidia/llama-nemotron-embed-vl-1b-v2 base_model:quantized:nvidia/llama-nemotron-embed-vl-1b-v2 license:other endpoints_compatible modelopt region:us