Nemotron-3.5-Embed-1B-BF16 API & Inference Endpoint

Description:

Nemotron-3.5-Embed-1B-BF16 is a versatile embedding model developed by NVIDIA for multimodal and multilingual question-answering retrieval. The model can embed a document page in the form of an image, text, or combined image–text input. Documents can be retrieved given a user query in text form. The model supports page images containing text, tables, charts, and infographics. For text retrieval, the model was evaluated across 34 languages: English, Arabic, Assamese, Bengali, Bulgarian, Chinese, Danish, Dutch, Finnish, French, German, Hindi, Hinglish, Indonesian, Italian, Japanese, Korean, Malay, Marathi, Nepali, Norwegian, Persian, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Ukrainian, Urdu, and Vietnamese. For image retrieval, it was evaluated across 18 languages: Arabic, Bengali, Chinese, English, Persian, Finnish, French, German, Hindi, Indonesian, Japanese, Korean, Russian, Spanish, Swahili, Telugu, Thai, and Yoruba. The model may support additional languages beyond these evaluation sets.

Among models of comparable size, Nemotron-3.5-Embed-1B-BF16 achieves state-of-the-art results across multiple multilingual and multimodal retrieval benchmarks. Read more details in our Blog Post.

This model is ready for commercial or non-commercial use.

License/Terms of Use:

Governing Download Terms: Use of the model is governed by the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1). Additional Information: The Ministral-3-3B-Instruct-2512-BF16 and Ministral-3-8B-Instruct-2512-BF16 base models are governed by the Apache License, Version 2.0.

Deployment Geography:

Global

Use Case:

The Nemotron-3.5-Embed-1B-BF16 is suitable for users who want to build a multimodal question-and-answer application over a large corpus, leveraging the latest dense retrieval technology. The input of the model is a text or a document image, and the output is a fixed-size embedding vector. The embedding model is a bi-encoder that supports context in textual format (e.g. the query or the OCR text of a page or a section of a document) or the image of a document page. Typically, the embedding model is used first to embed (vectorize) the whole corpus (document images or text chunks), and embeddings are stored in a vector database associated to its raw content (image or text). Then at inference time, the embedding model is used to embed the query. The model generates dense vector embeddings from text or image inputs, enabling multimodal retrieval, semantic search, and (agentic) RAG workflows.

Release Date:

Hugging Face 10/20/2026 via https://huggingface.co/nvidia/Nemotron-3.5-Embed-1B-BF16

Model Architecture:

Architecture Type: Transformer Network Architecture: Nemotron-3.5-Embed-1B-BF16 consists of a Pixtral vision encoder initialized from mistralai/Ministral-3-3B-Instruct-2512-BF16 and a language model initialized from nvidia/Nemotron-3-Embed-1B-BF16. Number of model parameters: 1.55B

The Nemotron-3.5-Embed-1B-BF16 model was distilled from the Nemotron-3.5-Embed-8B-BF16 embedding teacher using combined cosine distance (COS) and mean squared error (MSE) losses on multilingual text and image retrieval data. Its language-model component was initialized from Nemotron-3-Embed-1B-BF16 and kept frozen during distillation. Consequently, Nemotron-3.5-Embed-1B-BF16 shares the same text embedding space as Nemotron-3-Embed-1B-BF16 while adding image retrieval capabilities. The vision encoder and multimodal projection were fine-tuned on image and combined image-text datasets.

Input:

Input Type(s): Text, Image Input Format(s): Text: String; Image: Red, Green, Blue (RGB) Input Parameters: Text: One-Dimensional (1D), Image: Two-Dimensional (2D) Other Properties Related to Input: The model supports image and/or text inputs. For queries, the model accepts text input only. For documents, it accepts an image, text, or a combination of image + text. The default image longest_edge is 1,120 pixels, and it can be increased up to 1,540 pixels. The model’s max context length is 32,768 tokens.

Output:

Output Type(s): Embeddings
Output Format: Vector Output Parameters: One-Dimensional (1D) per input Other Properties Related to Output: Token-level hidden states are mean-pooled and then L2-normalized to produce one 2048-dimensional embedding vector for each input. The model also supports dynamic embedding sizes by truncating the vector from the end (e.g., retaining the first 1024 or 512 dimensions). The truncated embeddings remain effective for retrieval, provided they are L2-normalized after truncation.

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Installation

Create a Python 3.12 environment for the Transformers and Sentence Transformers examples:

bash

uv venv --python 3.12 .venv-transformerssource .venv-transformers/bin/activateuv pip install torch "transformers==5.20.0" accelerate pillow

And to install FlashAttention 2, you can either build it from source like so:

bash

uv pip install packaging ninjauv pip install flash-attn --no-build-isolation

or use a pre-built FlashAttention 2 kernel via the kernels package:

bash

uv pip install kernels

The examples use Flash Attention 2 and were tested with transformers==5.20.0. The checkpoint uses TokenizersBackend and does not require mistral_common.

Model training and evaluations used transformers==5.12.1. Example outputs can vary with hardware and runtime.

Transformers Usage

Generate embeddings for text queries and documents containing text, images, or both.

python

import torchimport torch.nn.functional as Ffrom PIL import Imagefrom transformers import AutoModel, AutoProcessorfrom transformers.image_utils import load_image MODEL_PATH = "nvidia/Nemotron-3.5-Embed-1B-BF16"  # Or a local checkpoint directory.DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"MAX_MODEL_LEN = 32768DEVICE = "cuda:0"  def main() -> None:    if not torch.cuda.is_available():        raise RuntimeError("This bfloat16 example requires a CUDA GPU.")     processor = AutoProcessor.from_pretrained(MODEL_PATH)     model = AutoModel.from_pretrained(        MODEL_PATH,        dtype=torch.bfloat16,        device_map={"": DEVICE},        attn_implementation="flash_attention_2",    ).eval()     def embed(        prefix: str,        text: str | None = None,        image: Image.Image | None = None,    ) -> torch.Tensor:        content = [] if image is None else [{"type": "image", "image": image}]         if text is not None:            content.append({"type": "text", "text": text})         inputs = processor.apply_chat_template(            [                {"role": "system", "content": prefix},                {"role": "user", "content": content},            ],            tokenize=True,            return_dict=True,            return_tensors="pt",        )        if inputs["input_ids"].shape[-1] > MAX_MODEL_LEN:            raise ValueError("Input exceeds 32768 tokens; shorten the text or resize the image.")        inputs = inputs.to(DEVICE)         if image is not None:            inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)         with torch.inference_mode():            hidden = model(**inputs).last_hidden_state            mask = inputs["attention_mask"].unsqueeze(-1)            embedding = (hidden * mask).sum(1) / mask.sum(1)         return F.normalize(embedding.float(), dim=-1)     image = load_image(IMAGE_URL)    query_embedding = embed("query:", "What is NVIDIA NeMo Framework?")    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."     document_embeddings = torch.cat(        [            embed("passage:", nemo_text, image),            embed("passage:", nemo_text),            embed("passage:", image=image),            embed("passage:", biology_text),        ]    )    scores = query_embedding @ document_embeddings.T    print(f"query_embedding.shape={tuple(query_embedding.shape)}")    print(f"document_embeddings.shape={tuple(document_embeddings.shape)}")    for name, score in zip(DOCUMENT_NAMES, scores[0]):        print(f"{name}_similarity={score.item():.6f}")  if __name__ == "__main__":    main()

Example output (scores can vary with hardware and runtime):

text

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521734nemo_text_similarity=0.457723nemo_image_similarity=0.509049biology_text_similarity=0.112573

Sentence Transformers Usage

In the same environment, install Sentence Transformers:

bash

uv pip install "sentence-transformers[image]>5.4" "transformers==5.20.0"

Encode text, images, or combined text and images. Image URLs are loaded automatically, and encode_query and encode_document apply the saved retrieval prefixes.

python

from sentence_transformers import SentenceTransformer model = SentenceTransformer(    "nvidia/Nemotron-3.5-Embed-1B-BF16",    device="cuda",    model_kwargs={"dtype": "bfloat16", "attn_implementation": "flash_attention_2"},) query = "What is NVIDIA NeMo Framework?"image_url = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."document_names = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]documents = [    {"image": image_url, "text": nemo_text},    nemo_text,    {"image": image_url},    biology_text,] query_embedding = model.encode_query([query])document_embeddings = model.encode_document(documents, batch_size=1) similarities = model.similarity(query_embedding, document_embeddings) print(f"query_embedding.shape={query_embedding.shape}")print(f"document_embeddings.shape={document_embeddings.shape}")for name, score in zip(document_names, similarities[0]):    print(f"{name}_similarity={score.item():.6f}")

Example output (BF16 scores can vary slightly with hardware, batching, and runtime):

text

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521564nemo_text_similarity=0.457218nemo_image_similarity=0.508792biology_text_similarity=0.112911

vLLM Usage

Generate embeddings for text, images, and combined image and text inputs using the vLLM Python API or an HTTP server.

Dependencies

Create a separate Python environment for vLLM. Set MODEL_PATH to the Hugging Face model ID or a local checkpoint directory:

bash

uv venv --python 3.12 .venv-vllmsource .venv-vllm/bin/activateuv pip install "vllm==0.32.0" "transformers==5.19.0" pillow httpx numpyexport MODEL_PATH="nvidia/Nemotron-3.5-Embed-1B-BF16"

These examples use vLLM 0.32.0, which requires transformers>=5.16.1,<5.20.0. Keep the vLLM environment separate from the Transformers 5.20.0 environment above. Image preprocessing uses the checkpoint's configured longest-edge limit of 1,120 pixels. The 32,768-token context includes both text and image tokens.

Offline Python

Use query: for text queries and passage: for documents. Format each input with the model's chat template and pass images through multi_modal_data:

python

import os import numpy as npfrom transformers import AutoProcessorfrom transformers.image_utils import load_imagefrom vllm import LLMfrom vllm.config import PoolerConfig MODEL_PATH = os.environ["MODEL_PATH"]DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"MAX_MODEL_LEN = 32768  def main() -> None:    processor = AutoProcessor.from_pretrained(MODEL_PATH)    model = LLM(        model=MODEL_PATH,        compilation_config={"compile_mm_encoder": True},        dtype="bfloat16",        pooler_config=PoolerConfig(            task="embed",            pooling_type="MEAN",            use_activation=True,        ),        max_model_len=MAX_MODEL_LEN,    )    image = load_image(IMAGE_URL)    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."    samples = [        ("query:", "What is NVIDIA NeMo Framework?", None),        ("passage:", nemo_text, image),        ("passage:", nemo_text, None),        ("passage:", None, image),        ("passage:", biology_text, None),    ]    prompts = []    for prefix, text, image in samples:        content = [] if image is None else [{"type": "image", "image": image}]        if text is not None:            content.append({"type": "text", "text": text})        conversation = [            {"role": "system", "content": prefix},            {"role": "user", "content": content},        ]        prompt = {"prompt": processor.apply_chat_template(conversation, tokenize=False)}        if image is not None:            prompt["multi_modal_data"] = {"image": image}        prompts.append(prompt)     # Preserve the template output without adding BOS/EOS tokens.    outputs = model.embed(prompts, tokenization_kwargs={"add_special_tokens": False})    embeddings = np.asarray([result.outputs.embedding for result in outputs], dtype=np.float32)    query_embedding, document_embeddings = embeddings[:1], embeddings[1:]    scores = query_embedding @ document_embeddings.T    print(f"query_embedding.shape={query_embedding.shape}")    print(f"document_embeddings.shape={document_embeddings.shape}")    for name, score in zip(DOCUMENT_NAMES, scores[0]):        print(f"{name}_similarity={score:.6f}")  if __name__ == "__main__":    main()

Example output (scores can vary with hardware and runtime):

text

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521628nemo_text_similarity=0.458030nemo_image_similarity=0.508873biology_text_similarity=0.112930

The example returns one query embedding and four document embeddings, each with 2,048 dimensions. The embeddings are L2-normalized, so their dot products give cosine similarity scores. Higher scores indicate greater similarity to the query.

Online Serving

Start a local embedding server:

bash

vllm serve "$MODEL_PATH" \    --served-model-name "nvidia/Nemotron-3.5-Embed-1B-BF16" \    --dtype bfloat16 \    --max-model-len 32768 \    --compilation-config '{"compile_mm_encoder":true}' \    --chat-template-content-format openai \    --host 127.0.0.1 \    --port 8000

After the server is ready, open another terminal in the same directory and activate the vLLM environment:

bash

source .venv-vllm/bin/activate

Run the following Python client to send the query and a batch of four documents to /v2/embed. input_type selects the query or document prefix from the checkpoint. The client sets truncate="END" to truncate text from the end. If image tokens alone exceed the context limit, reduce the image resolution.

python

import httpximport numpy as np MODEL_ID = "nvidia/Nemotron-3.5-Embed-1B-BF16"ENDPOINT = "http://127.0.0.1:8000/v2/embed"IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]  def embed(client: httpx.Client, input_type: str, inputs: list[dict]) -> np.ndarray:    response = client.post(        ENDPOINT,        json={            "model": MODEL_ID,            "input_type": input_type,            "inputs": inputs,            "embedding_types": ["float"],            "truncate": "END",        },    )    response.raise_for_status()    return np.asarray(response.json()["embeddings"]["float"], dtype=np.float32)  def main() -> None:    query = "What is NVIDIA NeMo Framework?"    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."    image_block = {"type": "image_url", "image_url": {"url": IMAGE_URL}}    documents = [        {"content": [image_block, {"type": "text", "text": nemo_text}]},        {"content": [{"type": "text", "text": nemo_text}]},        {"content": [image_block]},        {"content": [{"type": "text", "text": biology_text}]},    ]    with httpx.Client(timeout=120.0) as client:        query_embedding = embed(client, "query", [{"content": [{"type": "text", "text": query}]}])[0]        document_embeddings = embed(client, "document", documents)     print(f"query_embedding.shape={query_embedding.shape}")    print(f"document_embeddings.shape={document_embeddings.shape}")    for name, score in zip(DOCUMENT_NAMES, query_embedding @ document_embeddings.T):        print(f"{name}_similarity={score:.6f}")  if __name__ == "__main__":    main()

Example output (scores can vary with hardware and runtime):

text

query_embedding.shape=(2048,)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521529nemo_text_similarity=0.457598nemo_image_similarity=0.508731biology_text_similarity=0.112908

For the Transformers and Sentence Transformers examples, flash_attention_2 can cause CUDA errors or incorrect outputs with image inputs in Transformers 5.17.0, 5.18.0, and 5.19.0. Upgrade to transformers==5.20.0.

Software Integration:

Runtime Engine(s):

Transformers
Sentence Transformers
vLLM

Supported Hardware Microarchitecture Compatibility:

NVIDIA Ampere
NVIDIA Blackwell
NVIDIA Hopper

Supported Operating System(s): Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s):

Nemotron-3.5-Embed-1B-BF16

Training, Testing, and Evaluation Datasets:

Training Dataset:

Data Modality:

Image
Text

Image Training Data Size: 2.3M samples containing images, with or without accompanying text Text Training Data Size: 8.5M+ text-only data samples Data Collection Method by dataset: Automated, Manually-Labeled, Synthetic Labeling Method by dataset: Automated, Manually-Labeled, Synthetic Properties: Training was conducted using publicly available, commercially permissible datasets and synthetically generated datasets.

Public Datasets:

The language model of Nemotron-3.5-Embed-1B-BF16 was trained with text-only datasets that have been listed in Nemotron-3-Embed-1B-BF16's Model Card. In addition to these datasets we have used the following publicly available datasets to train the vision encoder and multimodal projector with image-only and image + text inputs.

Table with columns: Dataset name, Reference
Dataset name	Reference
ArxivQA	https://huggingface.co/datasets/MMInstruction/ArxivQA
ColPali-PDF	https://huggingface.co/datasets/vidore/colpali_train_set
InfoVQA	https://www.docvqa.org/datasets/infographicvqa
docmatix-ir	https://huggingface.co/datasets/Tevatron/docmatix-ir
Docmatix	https://huggingface.co/datasets/HuggingFaceM4/Docmatix
wiki-ss-nq	https://huggingface.co/datasets/Tevatron/wiki-ss-nq

Synthetic datasets were created either by generating queries from seed documents or by generating complete question–answer pairs through LLM-based prompting using the models listed below.

Testing Dataset:

Data Collection Method by dataset: Not Applicable
Labeling Method by dataset: Not Applicable
Properties: Not Applicable. Model quality was assessed using the evaluation benchmark datasets described in the Evaluation Dataset subsection.

Evaluation Dataset:

Benchmark:

Benchmark Score: NDCG@10

The Nemotron-3.5-Embed-1B-BF16 and Nemotron-3.5-Embed-8B-BF16 were evaluated with the models' default image longest_edge of 1,120 pixels. Qwen3-VL-Embedding-2B and Qwen3-VL-Embedding-8B were evaluated with max_pixels set to 1,843,200.

Data Collection Method by dataset: Automated, Manually-Labeled, Synthetic Labeling Method by dataset: Automated, Manually-Labeled, Synthetic Properties: ViDoRe V3 is a visual document retrieval benchmark covering 8 public and 2 private datasets across professional domains. MIRACL-VISION is a multilingual visual retrieval dataset for 18 different languages. It is an extension of MIRACL, a popular text-only multilingual retrieval dataset.

Inference:

Acceleration Engine: Transformers, PyTorch, vLLM Hardware Requirements (GPU Architecture, Model):

NVIDIA Ampere (A100 80GB)
NVIDIA Blackwell (GB200 186GB)
NVIDIA Hopper (H100 80GB)

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please make sure you have proper rights and permissions for all input image and video content; if image or video includes people, personal health information, or intellectual property, the image or video generated will not blur or maintain proportions of image subjects included.
For more detailed information on ethical considerations for this model, please see the Bias, Explainability, Privacy, and Safety & Security Subcards. Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

Bias

Table with columns: Field, Response
Field	Response
Participation considerations from adversely impacted groups protected classes in model design and testing:	None
Measures taken to mitigate against unwanted bias:	None
Bias Metric (If Measured):	Not Applicable

Explainability

Table with columns: Field, Response
Field	Response
Intended Task/Domain:	Document and query embedding for question and answer retrieval.
Model Type:	Transformer encoder
Intended Users:	Generative AI creators working with conversational AI models - users who want to build a multilingual and multimodal question and answer application over a large document corpus, leveraging the latest dense retrieval technologies.
Output:	Array of float numbers (Dense Vector Representation for the input text or image)
Describe how the model works:	Model transforms the tokenized input into a dense vector representation.
List the groups (or group characteristics) for which this was tested to produce comparable outcomes:	Not Applicable
Technical Limitations & Mitigation:	The model’s max sequence length is 32768. Therefore, the longer inputs should be truncated.
Verified to have met prescribed NVIDIA quality standards:	Yes
Performance Metrics:	Accuracy, Latency and Throughput
Potential Known Risks:	This model does not always guarantee to retrieve the correct document(s) for a given query.
Licensing:	Use of the model is governed by the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1). Additional Information: The Ministral-3-3B-Instruct-2512-BF16 and Ministral-3-8B-Instruct-2512-BF16 base models are governed by the Apache License, Version 2.0.

Privacy

The datasets used to train this model were reviewed before release. Please review NVIDIA’s Privacy Policy (https://www.nvidia.com/en-us/about-nvidia/privacy-policy/) for more information.

Safety

Table with columns: Field, Response
Field	Response
Model Application Field(s):	Document Embedding for Retrieval. User queries can be text and documents can be text, document page images, charts, tables, and infographics.
Describe the life critical impact (if present).	Not Applicable
Use Case Restrictions:	Use of the model is governed by the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1). Additional Information: The Ministral-3-3B-Instruct-2512-BF16 and Ministral-3-8B-Instruct-2512-BF16 base models are governed by the Apache License, Version 2.0.
Model and dataset restrictions:	The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.

Description:

Among models of comparable size, Nemotron-3.5-Embed-1B-BF16 achieves state-of-the-art results across multiple multilingual and multimodal retrieval benchmarks. Read more details in our Blog Post.

This model is ready for commercial or non-commercial use.

License/Terms of Use:

Deployment Geography:

Global

Use Case:

Release Date:

Hugging Face 10/20/2026 via https://huggingface.co/nvidia/Nemotron-3.5-Embed-1B-BF16

Model Architecture:

Input:

Output:

Installation

Create a Python 3.12 environment for the Transformers and Sentence Transformers examples:

bash

uv venv --python 3.12 .venv-transformerssource .venv-transformers/bin/activateuv pip install torch "transformers==5.20.0" accelerate pillow

uv venv --python 3.12 .venv-transformerssource .venv-transformers/bin/activateuv pip install torch "transformers==5.20.0" accelerate pillow

And to install FlashAttention 2, you can either build it from source like so:

bash

uv pip install packaging ninjauv pip install flash-attn --no-build-isolation

uv pip install packaging ninjauv pip install flash-attn --no-build-isolation

or use a pre-built FlashAttention 2 kernel via the kernels package:

bash

uv pip install kernels

The examples use Flash Attention 2 and were tested with transformers==5.20.0. The checkpoint uses TokenizersBackend and does not require mistral_common.

Model training and evaluations used transformers==5.12.1. Example outputs can vary with hardware and runtime.

Transformers Usage

Generate embeddings for text queries and documents containing text, images, or both.

python

import torchimport torch.nn.functional as Ffrom PIL import Imagefrom transformers import AutoModel, AutoProcessorfrom transformers.image_utils import load_image MODEL_PATH = "nvidia/Nemotron-3.5-Embed-1B-BF16"  # Or a local checkpoint directory.DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"MAX_MODEL_LEN = 32768DEVICE = "cuda:0"  def main() -> None:    if not torch.cuda.is_available():        raise RuntimeError("This bfloat16 example requires a CUDA GPU.")     processor = AutoProcessor.from_pretrained(MODEL_PATH)     model = AutoModel.from_pretrained(        MODEL_PATH,        dtype=torch.bfloat16,        device_map={"": DEVICE},        attn_implementation="flash_attention_2",    ).eval()     def embed(        prefix: str,        text: str | None = None,        image: Image.Image | None = None,    ) -> torch.Tensor:        content = [] if image is None else [{"type": "image", "image": image}]         if text is not None:            content.append({"type": "text", "text": text})         inputs = processor.apply_chat_template(            [                {"role": "system", "content": prefix},                {"role": "user", "content": content},            ],            tokenize=True,            return_dict=True,            return_tensors="pt",        )        if inputs["input_ids"].shape[-1] > MAX_MODEL_LEN:            raise ValueError("Input exceeds 32768 tokens; shorten the text or resize the image.")        inputs = inputs.to(DEVICE)         if image is not None:            inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)         with torch.inference_mode():            hidden = model(**inputs).last_hidden_state            mask = inputs["attention_mask"].unsqueeze(-1)            embedding = (hidden * mask).sum(1) / mask.sum(1)         return F.normalize(embedding.float(), dim=-1)     image = load_image(IMAGE_URL)    query_embedding = embed("query:", "What is NVIDIA NeMo Framework?")    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."     document_embeddings = torch.cat(        [            embed("passage:", nemo_text, image),            embed("passage:", nemo_text),            embed("passage:", image=image),            embed("passage:", biology_text),        ]    )    scores = query_embedding @ document_embeddings.T    print(f"query_embedding.shape={tuple(query_embedding.shape)}")    print(f"document_embeddings.shape={tuple(document_embeddings.shape)}")    for name, score in zip(DOCUMENT_NAMES, scores[0]):        print(f"{name}_similarity={score.item():.6f}")  if __name__ == "__main__":    main()

import torchimport torch.nn.functional as Ffrom PIL import Imagefrom transformers import AutoModel, AutoProcessorfrom transformers.image_utils import load_image MODEL_PATH = "nvidia/Nemotron-3.5-Embed-1B-BF16"  # Or a local checkpoint directory.DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"MAX_MODEL_LEN = 32768DEVICE = "cuda:0"  def main() -> None:    if not torch.cuda.is_available():        raise RuntimeError("This bfloat16 example requires a CUDA GPU.")     processor = AutoProcessor.from_pretrained(MODEL_PATH)     model = AutoModel.from_pretrained(        MODEL_PATH,        dtype=torch.bfloat16,        device_map={"": DEVICE},        attn_implementation="flash_attention_2",    ).eval()     def embed(        prefix: str,        text: str | None = None,        image: Image.Image | None = None,    ) -> torch.Tensor:        content = [] if image is None else [{"type": "image", "image": image}]         if text is not None:            content.append({"type": "text", "text": text})         inputs = processor.apply_chat_template(            [                {"role": "system", "content": prefix},                {"role": "user", "content": content},            ],            tokenize=True,            return_dict=True,            return_tensors="pt",        )        if inputs["input_ids"].shape[-1] > MAX_MODEL_LEN:            raise ValueError("Input exceeds 32768 tokens; shorten the text or resize the image.")        inputs = inputs.to(DEVICE)         if image is not None:            inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)         with torch.inference_mode():            hidden = model(**inputs).last_hidden_state            mask = inputs["attention_mask"].unsqueeze(-1)            embedding = (hidden * mask).sum(1) / mask.sum(1)         return F.normalize(embedding.float(), dim=-1)     image = load_image(IMAGE_URL)    query_embedding = embed("query:", "What is NVIDIA NeMo Framework?")    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."     document_embeddings = torch.cat(        [            embed("passage:", nemo_text, image),            embed("passage:", nemo_text),            embed("passage:", image=image),            embed("passage:", biology_text),        ]    )    scores = query_embedding @ document_embeddings.T    print(f"query_embedding.shape={tuple(query_embedding.shape)}")    print(f"document_embeddings.shape={tuple(document_embeddings.shape)}")    for name, score in zip(DOCUMENT_NAMES, scores[0]):        print(f"{name}_similarity={score.item():.6f}")  if __name__ == "__main__":    main()

Example output (scores can vary with hardware and runtime):

text

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521734nemo_text_similarity=0.457723nemo_image_similarity=0.509049biology_text_similarity=0.112573

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521734nemo_text_similarity=0.457723nemo_image_similarity=0.509049biology_text_similarity=0.112573

Sentence Transformers Usage

In the same environment, install Sentence Transformers:

bash

uv pip install "sentence-transformers[image]>5.4" "transformers==5.20.0"

Encode text, images, or combined text and images. Image URLs are loaded automatically, and encode_query and encode_document apply the saved retrieval prefixes.

python

from sentence_transformers import SentenceTransformer model = SentenceTransformer(    "nvidia/Nemotron-3.5-Embed-1B-BF16",    device="cuda",    model_kwargs={"dtype": "bfloat16", "attn_implementation": "flash_attention_2"},) query = "What is NVIDIA NeMo Framework?"image_url = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."document_names = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]documents = [    {"image": image_url, "text": nemo_text},    nemo_text,    {"image": image_url},    biology_text,] query_embedding = model.encode_query([query])document_embeddings = model.encode_document(documents, batch_size=1) similarities = model.similarity(query_embedding, document_embeddings) print(f"query_embedding.shape={query_embedding.shape}")print(f"document_embeddings.shape={document_embeddings.shape}")for name, score in zip(document_names, similarities[0]):    print(f"{name}_similarity={score.item():.6f}")

from sentence_transformers import SentenceTransformer model = SentenceTransformer(    "nvidia/Nemotron-3.5-Embed-1B-BF16",    device="cuda",    model_kwargs={"dtype": "bfloat16", "attn_implementation": "flash_attention_2"},) query = "What is NVIDIA NeMo Framework?"image_url = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."document_names = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]documents = [    {"image": image_url, "text": nemo_text},    nemo_text,    {"image": image_url},    biology_text,] query_embedding = model.encode_query([query])document_embeddings = model.encode_document(documents, batch_size=1) similarities = model.similarity(query_embedding, document_embeddings) print(f"query_embedding.shape={query_embedding.shape}")print(f"document_embeddings.shape={document_embeddings.shape}")for name, score in zip(document_names, similarities[0]):    print(f"{name}_similarity={score.item():.6f}")

Example output (BF16 scores can vary slightly with hardware, batching, and runtime):

text

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521564nemo_text_similarity=0.457218nemo_image_similarity=0.508792biology_text_similarity=0.112911

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521564nemo_text_similarity=0.457218nemo_image_similarity=0.508792biology_text_similarity=0.112911

vLLM Usage

Generate embeddings for text, images, and combined image and text inputs using the vLLM Python API or an HTTP server.

Dependencies

Create a separate Python environment for vLLM. Set MODEL_PATH to the Hugging Face model ID or a local checkpoint directory:

bash

uv venv --python 3.12 .venv-vllmsource .venv-vllm/bin/activateuv pip install "vllm==0.32.0" "transformers==5.19.0" pillow httpx numpyexport MODEL_PATH="nvidia/Nemotron-3.5-Embed-1B-BF16"

uv venv --python 3.12 .venv-vllmsource .venv-vllm/bin/activateuv pip install "vllm==0.32.0" "transformers==5.19.0" pillow httpx numpyexport MODEL_PATH="nvidia/Nemotron-3.5-Embed-1B-BF16"

Offline Python

Use query: for text queries and passage: for documents. Format each input with the model's chat template and pass images through multi_modal_data:

python

import os import numpy as npfrom transformers import AutoProcessorfrom transformers.image_utils import load_imagefrom vllm import LLMfrom vllm.config import PoolerConfig MODEL_PATH = os.environ["MODEL_PATH"]DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"MAX_MODEL_LEN = 32768  def main() -> None:    processor = AutoProcessor.from_pretrained(MODEL_PATH)    model = LLM(        model=MODEL_PATH,        compilation_config={"compile_mm_encoder": True},        dtype="bfloat16",        pooler_config=PoolerConfig(            task="embed",            pooling_type="MEAN",            use_activation=True,        ),        max_model_len=MAX_MODEL_LEN,    )    image = load_image(IMAGE_URL)    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."    samples = [        ("query:", "What is NVIDIA NeMo Framework?", None),        ("passage:", nemo_text, image),        ("passage:", nemo_text, None),        ("passage:", None, image),        ("passage:", biology_text, None),    ]    prompts = []    for prefix, text, image in samples:        content = [] if image is None else [{"type": "image", "image": image}]        if text is not None:            content.append({"type": "text", "text": text})        conversation = [            {"role": "system", "content": prefix},            {"role": "user", "content": content},        ]        prompt = {"prompt": processor.apply_chat_template(conversation, tokenize=False)}        if image is not None:            prompt["multi_modal_data"] = {"image": image}        prompts.append(prompt)     # Preserve the template output without adding BOS/EOS tokens.    outputs = model.embed(prompts, tokenization_kwargs={"add_special_tokens": False})    embeddings = np.asarray([result.outputs.embedding for result in outputs], dtype=np.float32)    query_embedding, document_embeddings = embeddings[:1], embeddings[1:]    scores = query_embedding @ document_embeddings.T    print(f"query_embedding.shape={query_embedding.shape}")    print(f"document_embeddings.shape={document_embeddings.shape}")    for name, score in zip(DOCUMENT_NAMES, scores[0]):        print(f"{name}_similarity={score:.6f}")  if __name__ == "__main__":    main()

import os import numpy as npfrom transformers import AutoProcessorfrom transformers.image_utils import load_imagefrom vllm import LLMfrom vllm.config import PoolerConfig MODEL_PATH = os.environ["MODEL_PATH"]DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"MAX_MODEL_LEN = 32768  def main() -> None:    processor = AutoProcessor.from_pretrained(MODEL_PATH)    model = LLM(        model=MODEL_PATH,        compilation_config={"compile_mm_encoder": True},        dtype="bfloat16",        pooler_config=PoolerConfig(            task="embed",            pooling_type="MEAN",            use_activation=True,        ),        max_model_len=MAX_MODEL_LEN,    )    image = load_image(IMAGE_URL)    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."    samples = [        ("query:", "What is NVIDIA NeMo Framework?", None),        ("passage:", nemo_text, image),        ("passage:", nemo_text, None),        ("passage:", None, image),        ("passage:", biology_text, None),    ]    prompts = []    for prefix, text, image in samples:        content = [] if image is None else [{"type": "image", "image": image}]        if text is not None:            content.append({"type": "text", "text": text})        conversation = [            {"role": "system", "content": prefix},            {"role": "user", "content": content},        ]        prompt = {"prompt": processor.apply_chat_template(conversation, tokenize=False)}        if image is not None:            prompt["multi_modal_data"] = {"image": image}        prompts.append(prompt)     # Preserve the template output without adding BOS/EOS tokens.    outputs = model.embed(prompts, tokenization_kwargs={"add_special_tokens": False})    embeddings = np.asarray([result.outputs.embedding for result in outputs], dtype=np.float32)    query_embedding, document_embeddings = embeddings[:1], embeddings[1:]    scores = query_embedding @ document_embeddings.T    print(f"query_embedding.shape={query_embedding.shape}")    print(f"document_embeddings.shape={document_embeddings.shape}")    for name, score in zip(DOCUMENT_NAMES, scores[0]):        print(f"{name}_similarity={score:.6f}")  if __name__ == "__main__":    main()

Example output (scores can vary with hardware and runtime):

text

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521628nemo_text_similarity=0.458030nemo_image_similarity=0.508873biology_text_similarity=0.112930

query_embedding.shape=(1, 2048)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521628nemo_text_similarity=0.458030nemo_image_similarity=0.508873biology_text_similarity=0.112930

Online Serving

Start a local embedding server:

bash

vllm serve "$MODEL_PATH" \    --served-model-name "nvidia/Nemotron-3.5-Embed-1B-BF16" \    --dtype bfloat16 \    --max-model-len 32768 \    --compilation-config '{"compile_mm_encoder":true}' \    --chat-template-content-format openai \    --host 127.0.0.1 \    --port 8000

vllm serve "$MODEL_PATH" \    --served-model-name "nvidia/Nemotron-3.5-Embed-1B-BF16" \    --dtype bfloat16 \    --max-model-len 32768 \    --compilation-config '{"compile_mm_encoder":true}' \    --chat-template-content-format openai \    --host 127.0.0.1 \    --port 8000

After the server is ready, open another terminal in the same directory and activate the vLLM environment:

bash

source .venv-vllm/bin/activate

python

import httpximport numpy as np MODEL_ID = "nvidia/Nemotron-3.5-Embed-1B-BF16"ENDPOINT = "http://127.0.0.1:8000/v2/embed"IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]  def embed(client: httpx.Client, input_type: str, inputs: list[dict]) -> np.ndarray:    response = client.post(        ENDPOINT,        json={            "model": MODEL_ID,            "input_type": input_type,            "inputs": inputs,            "embedding_types": ["float"],            "truncate": "END",        },    )    response.raise_for_status()    return np.asarray(response.json()["embeddings"]["float"], dtype=np.float32)  def main() -> None:    query = "What is NVIDIA NeMo Framework?"    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."    image_block = {"type": "image_url", "image_url": {"url": IMAGE_URL}}    documents = [        {"content": [image_block, {"type": "text", "text": nemo_text}]},        {"content": [{"type": "text", "text": nemo_text}]},        {"content": [image_block]},        {"content": [{"type": "text", "text": biology_text}]},    ]    with httpx.Client(timeout=120.0) as client:        query_embedding = embed(client, "query", [{"content": [{"type": "text", "text": query}]}])[0]        document_embeddings = embed(client, "document", documents)     print(f"query_embedding.shape={query_embedding.shape}")    print(f"document_embeddings.shape={document_embeddings.shape}")    for name, score in zip(DOCUMENT_NAMES, query_embedding @ document_embeddings.T):        print(f"{name}_similarity={score:.6f}")  if __name__ == "__main__":    main()

import httpximport numpy as np MODEL_ID = "nvidia/Nemotron-3.5-Embed-1B-BF16"ENDPOINT = "http://127.0.0.1:8000/v2/embed"IMAGE_URL = "https://docs.nvidia.com/nemo-framework/user-guide/24.07/_images/nemo-llm-mm-stack.png"DOCUMENT_NAMES = ["nemo_image_text", "nemo_text", "nemo_image", "biology_text"]  def embed(client: httpx.Client, input_type: str, inputs: list[dict]) -> np.ndarray:    response = client.post(        ENDPOINT,        json={            "model": MODEL_ID,            "input_type": input_type,            "inputs": inputs,            "embedding_types": ["float"],            "truncate": "END",        },    )    response.raise_for_status()    return np.asarray(response.json()["embeddings"]["float"], dtype=np.float32)  def main() -> None:    query = "What is NVIDIA NeMo Framework?"    nemo_text = "NeMo Framework offers comprehensive functionalities for developing both LLMs and Multimodal Models."    biology_text = "A biological foundation model designed to analyze and generate DNA, RNA, and protein sequences."    image_block = {"type": "image_url", "image_url": {"url": IMAGE_URL}}    documents = [        {"content": [image_block, {"type": "text", "text": nemo_text}]},        {"content": [{"type": "text", "text": nemo_text}]},        {"content": [image_block]},        {"content": [{"type": "text", "text": biology_text}]},    ]    with httpx.Client(timeout=120.0) as client:        query_embedding = embed(client, "query", [{"content": [{"type": "text", "text": query}]}])[0]        document_embeddings = embed(client, "document", documents)     print(f"query_embedding.shape={query_embedding.shape}")    print(f"document_embeddings.shape={document_embeddings.shape}")    for name, score in zip(DOCUMENT_NAMES, query_embedding @ document_embeddings.T):        print(f"{name}_similarity={score:.6f}")  if __name__ == "__main__":    main()

Example output (scores can vary with hardware and runtime):

text

query_embedding.shape=(2048,)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521529nemo_text_similarity=0.457598nemo_image_similarity=0.508731biology_text_similarity=0.112908

query_embedding.shape=(2048,)document_embeddings.shape=(4, 2048)nemo_image_text_similarity=0.521529nemo_text_similarity=0.457598nemo_image_similarity=0.508731biology_text_similarity=0.112908

Software Integration:

Runtime Engine(s):

Transformers
Sentence Transformers
vLLM

Supported Hardware Microarchitecture Compatibility:

NVIDIA Ampere
NVIDIA Blackwell
NVIDIA Hopper

Supported Operating System(s): Linux

Model Version(s):

Nemotron-3.5-Embed-1B-BF16

Training, Testing, and Evaluation Datasets:

Training Dataset:

Data Modality:

Image
Text

Public Datasets:

Table with columns: Dataset name, Reference
Dataset name	Reference
ArxivQA	https://huggingface.co/datasets/MMInstruction/ArxivQA
ColPali-PDF	https://huggingface.co/datasets/vidore/colpali_train_set
InfoVQA	https://www.docvqa.org/datasets/infographicvqa
docmatix-ir	https://huggingface.co/datasets/Tevatron/docmatix-ir
Docmatix	https://huggingface.co/datasets/HuggingFaceM4/Docmatix
wiki-ss-nq	https://huggingface.co/datasets/Tevatron/wiki-ss-nq

Synthetic datasets were created either by generating queries from seed documents or by generating complete question–answer pairs through LLM-based prompting using the models listed below.

Testing Dataset:

Evaluation Dataset:

Benchmark:

Benchmark Score: NDCG@10

Inference:

Acceleration Engine: Transformers, PyTorch, vLLM Hardware Requirements (GPU Architecture, Model):

NVIDIA Ampere (A100 80GB)
NVIDIA Blackwell (GB200 186GB)
NVIDIA Hopper (H100 80GB)

Ethical Considerations:

Bias

Table with columns: Field, Response
Field	Response
Participation considerations from adversely impacted groups protected classes in model design and testing:	None
Measures taken to mitigate against unwanted bias:	None
Bias Metric (If Measured):	Not Applicable

Explainability

Table with columns: Field, Response
Field	Response
Intended Task/Domain:	Document and query embedding for question and answer retrieval.
Model Type:	Transformer encoder
Intended Users:	Generative AI creators working with conversational AI models - users who want to build a multilingual and multimodal question and answer application over a large document corpus, leveraging the latest dense retrieval technologies.
Output:	Array of float numbers (Dense Vector Representation for the input text or image)
Describe how the model works:	Model transforms the tokenized input into a dense vector representation.
List the groups (or group characteristics) for which this was tested to produce comparable outcomes:	Not Applicable
Technical Limitations & Mitigation:	The model’s max sequence length is 32768. Therefore, the longer inputs should be truncated.
Verified to have met prescribed NVIDIA quality standards:	Yes
Performance Metrics:	Accuracy, Latency and Throughput
Potential Known Risks:	This model does not always guarantee to retrieve the correct document(s) for a given query.
Licensing:	Use of the model is governed by the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1). Additional Information: The Ministral-3-3B-Instruct-2512-BF16 and Ministral-3-8B-Instruct-2512-BF16 base models are governed by the Apache License, Version 2.0.

Privacy

The datasets used to train this model were reviewed before release. Please review NVIDIA’s Privacy Policy (https://www.nvidia.com/en-us/about-nvidia/privacy-policy/) for more information.

Safety

Table with columns: Field, Response
Field	Response
Model Application Field(s):	Document Embedding for Retrieval. User queries can be text and documents can be text, document page images, charts, tables, and infographics.
Describe the life critical impact (if present).	Not Applicable
Use Case Restrictions:	Use of the model is governed by the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1). Additional Information: The Ministral-3-3B-Instruct-2512-BF16 and Ministral-3-8B-Instruct-2512-BF16 base models are governed by the Apache License, Version 2.0.
Model and dataset restrictions:	The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.

Nemotron-3.5-Embed-1B-BF16

README

Description:

License/Terms of Use:

Deployment Geography:

Use Case:

Release Date:

Model Architecture:

Input:

Output:

Installation

Transformers Usage

Sentence Transformers Usage

vLLM Usage

Dependencies

Offline Python

Online Serving

Software Integration:

Model Version(s):

Training, Testing, and Evaluation Datasets:

Training Dataset:

Public Datasets:

Testing Dataset:

Evaluation Dataset:

Inference:

Ethical Considerations:

Bias

Explainability

Privacy

Safety

Explore FriendliAI today

README

Description:

License/Terms of Use:

Deployment Geography:

Use Case:

Release Date:

Model Architecture:

Input:

Output:

Installation

Transformers Usage

Sentence Transformers Usage

vLLM Usage

Dependencies

Offline Python

Online Serving

Software Integration:

Model Version(s):

Training, Testing, and Evaluation Datasets:

Training Dataset:

Public Datasets:

Testing Dataset:

Evaluation Dataset:

Inference:

Ethical Considerations:

Bias

Explainability

Privacy

Safety