llama-nemotron-colembed-vl-3b-v2
6.1K
16
llama_nemotron_vl
by
nvidia
Image Model
OTHER
3B params
New
6K downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
7GB+ RAM
Mobile
Laptop
Server
Quick Summary
AI model with specialized capabilities.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
3GB+ RAM
Training Data Analysis
š” Average (4.8/10)
Researched training datasets used by llama-nemotron-colembed-vl-3b-v2 with quality assessment
Specialized For
general
science
multilingual
reasoning
Training Datasets (4)
common crawl
š“ 2.5/10
general
science
Key Strengths
- ā¢Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
- ā¢Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
- ā¢Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...
Considerations
- ā¢Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
- ā¢Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...
c4
šµ 6/10
general
multilingual
Key Strengths
- ā¢Scale and Accessibility: 750GB of publicly available, filtered text
- ā¢Systematic Filtering: Documented heuristics enable reproducibility
- ā¢Language Diversity: Despite English-only, captures diverse writing styles
Considerations
- ā¢English-Only: Limits multilingual applications
- ā¢Filtering Limitations: Offensive content and low-quality text remain despite filtering
wikipedia
š” 5/10
science
multilingual
Key Strengths
- ā¢High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
- ā¢Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
- ā¢Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...
Considerations
- ā¢Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
- ā¢Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...
arxiv
š” 5.5/10
science
reasoning
Key Strengths
- ā¢Scientific Authority: Peer-reviewed content from established repository
- ā¢Domain-Specific: Specialized vocabulary and concepts
- ā¢Mathematical Content: Includes complex equations and notation
Considerations
- ā¢Specialized: Primarily technical and mathematical content
- ā¢English-Heavy: Predominantly English-language papers
Explore our comprehensive training dataset analysis
View All DatasetsCode Examples
bash
pip install -U datasets polars
pip install -U pydanticEvaluation Resultsbash
pip install "mteb>=2.6.0, <3.0.0"
# Evaluates with Vidore V1 and V2
CUDA_VISIBLE_DEVICES=0; python3 mteb2_eval.py --model_name nvidia/llama-nemotron-colembed-vl-3b-v2 --batch_size 16 --benchmark "VisualDocumentRetrieval"
# Evaluates with Vidore V3
CUDA_VISIBLE_DEVICES=0; python3 mteb2_eval.py --model_name nvidia/llama-nemotron-colembed-vl-3b-v2 --batch_size 16 --benchmark "ViDoRe(v3)"
# Evaluates with a specific task/dataset of Vidore V3: Vidore3ComputerScienceRetrieval
CUDA_VISIBLE_DEVICES=0; python3 mteb2_eval.py --model_name nvidia/llama-nemotron-colembed-vl-3b-v2 --batch_size 16 --benchmark "ViDoRe(v3)" --task-list Vidore3ComputerScienceRetrievalDeploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.