Sentence Similarity
sentence-transformers
Safetensors
Transformers
multilingual
llama_nemotron_vl
feature-extraction
retrieval
visual document retrieval
vlm embedding
page image embedding
text embedding
semantic search
question-answering retrieval
rag
custom_code
Instructions to use novelcore/chimera-vdr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use novelcore/chimera-vdr with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("novelcore/chimera-vdr", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use novelcore/chimera-vdr with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("novelcore/chimera-vdr", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from novelcore/chimera-vdr: direct link, hf CLI and curl.
- Browser
- Download file 549 Bytes
-
https://huggingface.co/novelcore/chimera-vdr/resolve/main/processor_config.json
- Command line
-
hf download hf://novelcore/chimera-vdr/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/novelcore/chimera-vdr/resolve/main/processor_config.json
549 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_llama_nemotron_vl.LlamaNemotronVLProcessor" | |
| }, | |
| "dynamic_image_size": true, | |
| "image_size": 512, | |
| "max_input_tiles": 6, | |
| "norm_type": "siglip", | |
| "num_channels": 3, | |
| "num_image_token": 256, | |
| "p_max_length": 4096, | |
| "pad_to_multiple_of": null, | |
| "padding": true, | |
| "passage_prefix": "passage:", | |
| "processor_class": "LlamaNemotronVLProcessor", | |
| "q_max_length": 512, | |
| "query_prefix": "query:", | |
| "system_message": "", | |
| "template": "bidirectional-llama-retriever", | |
| "use_thumbnail": true | |
| } | |