Welcome to UCR Research Computing Artificial Intelligence (AI) and Machine Learning (ML) Resources. Explore the latest technologies, open-source models, and software platforms that empower your research and innovation.
Run Your Own Open-Source LLM Today
Learn how to run your own copy of an open-source large language model on UCR Ursa Major or your workstation.
How To Run Offline LLMs
Explore the leading AI chatbots designed to support your research needs.
Warning: Ensure you have the necessary permissions and take appropriate steps before using AI chatbots with sensitive or proprietary data.
Google Gemini is our featured AI chatbot for supporting your research needs. Its advanced natural language understanding and generation capabilities are highly effective for synthesizing complex information, drafting reports, analyzing text, and exploring diverse research topics.
Crucial Privacy Information: We have a Business Associate Agreement (BAA) in place with Google for our institutional use of Gemini. This agreement contractually guarantees that any data you input into Google Gemini through our designated channels will not be used by Google for training its AI models. Your research data remains private and confidential, aligning with our commitment to data security and privacy.
Chatbot | Description |
---|---|
ChatGPT | Versatile and widely adopted for detailed conversations, research assistance, and creative tasks. |
Claude | Renowned for its contextual understanding and nuance in dialogue, ideal for complex inquiries. |
Perplexity | Specializes in natural language queries with quick, informative responses, often citing sources. |
Harness the power of advanced software tools tailored to leverage HPC clusters and accelerate AI/ML research.
Note: Some installations and configurations may require advanced setup. Contact us at research-computing@ucr.edu for assistance.
Software | Use Case | Example Command |
---|---|---|
TensorFlow | Deep Learning | tensorflow_model_server --port=8500 --model_name=my_model --model_base_path=/models/my_model |
PyTorch | Machine Learning Models | python -m torch.distributed.launch --nproc_per_node=<NUM_GPUS> my_train_script.py |
Horovod | Distributed Training | horovodrun -np 4 -H localhost:4 python train.py |
CUDA | Parallel Computing | nvcc my_cuda_program.cu -o my_cuda_program |
Hugging Face Transformers | Natural Language Processing | transformers-cli convert --model_type bert --tf_checkpoint /path/to/checkpoint --config /path/to/bert_config.json --pytorch_dump_output /path/to/pytorch_model.bin |
Software | Use Case | Example Command |
---|---|---|
AlphaFold | Protein Structure Prediction | alphafold --fasta_path=my_sequence.fasta --output_dir=output |
FreeSurfer | Neuroimaging Analysis | recon-all -s subject_name -i input_volume.nii -all |
Software | Use Case | Example Command |
---|---|---|
GDAL | Geospatial Data Processing | gdal_translate -of GTiff input.tif output.tif |
Pangeo | Climate & Ocean Science | Deploy on cloud platforms for scalable data processing; see documentation for examples. |
Software | Use Case | Example Command |
---|---|---|
GROMACS | Molecular Dynamics | gmx mdrun -s topol.tpr -deffnm output |
Quantum ESPRESSO | Materials Modeling | pw.x -in Si.scf.in > Si.scf.out |
Software | Use Case | Example Command or Description |
---|---|---|
SpaCy | NLP & Text Processing | High-performance syntactic analysis and entity recognition. |
Gensim | Topic Modeling & Similarity | Ideal for unsupervised topic modeling and document similarity tasks. |
TextBlob | Simplified Text Processing | Provides an intuitive interface for sentiment analysis and text processing. |
NLTK | Natural Language Toolkit | Offers extensive corpora and lexical resources for language processing. |
Discover state-of-the-art open-source models that are driving innovation across disciplines—from text generation to image synthesis and beyond.
Run your own open-source LLM on UCR Ursa Major or your workstation today!
How To Run Offline LLMs
Name | Description | Name | Description |
---|---|---|---|
google/gemma-7b | Text Generation | ByteDance/SDXL-Lightning | Text-to-Image Generation |
bigcode/starcoder2-15b | Code & Text Generation | playgroundai/playground-v2.5-1024px-aesthetic | Artistic Text-to-Image |
google/gemma-2b | Text Generation | stabilityai/stable-video-diffusion-img2vid-xt | Image-to-Video Synthesis |
meta-llama/Llama-2-7b-chat-hf | Conversational AI | mistralai/Mixtral-8x7B-Instruct-v0.1 | Instruction-Tuned Text Generation |
Explore foundational tasks and the state-of-the-art models across key AI domains:
Advance your AI applications with these state-of-the-art development tools:
Tool Name | Description | Application |
---|---|---|
Flowise AI | Build and deploy LLM applications on custom data, with interactive workflows for PDF Q&A. | Rapid prototyping of LLM-powered apps |
LangChain | A powerful framework for building applications around language models, with integrations for embeddings and tokenization. | Simplifies LLM-based application development |
Vector Stores | Manage and retrieve vector embeddings efficiently—crucial for RAG and similarity search models. | Enhances retrieval-augmented generation |
Embedding Tools | Generate high-quality vector embeddings from textual data for better model performance. | Improves NLP model understanding and performance |
Tokenization Libraries | Convert text to tokens using optimized libraries that power modern language models. | Essential for data preprocessing in LLM training |
Fine-Tuning & Hosting | Customize pre-trained models and host them for inference using cloud platforms like GCP Vertex AI. | Tailors AI models to specific research tasks |
Tip: Experiment with these development tools to find the optimal setup for your projects—innovation often emerges from blending multiple approaches.
Tool Name | Description | Application in Research |
---|---|---|
Notebook LM | An AI-first interactive notebook for summarizing information and generating insights from complex datasets. | Ideal for synthesizing research findings |
Other Tools | Emerging tools to enhance retrieval and synthesis; check our Knowledge Base for the latest updates. |
Discover AI-powered image generation tools that turn textual descriptions into vivid visuals:
AI Tool | Application | Description |
---|---|---|
DALL·E 3 | Image Generation | Generates high-quality images from textual prompts with remarkable creativity. |
Stable Diffusion XL | Image Synthesis | State-of-the-art image synthesis that produces detailed and imaginative visuals from user inputs. |
MidJourney | Artistic Image Creation | Blends art and AI to create visually striking and creative images based on text descriptions. |
Explore how AI is transforming video content creation:
AI Tool | Application | Description |
---|---|---|
Kaiber AI | Video Generation | Transforms textual prompts into engaging, dynamic video content with minimal user input. |
DeepBrain AI | Video Synthesis | Produces lifelike videos, including virtual human content, for various research and communication needs. |
OpenAI’s Sora | Video Generation | (Upcoming) Promising next-generation video synthesis capabilities from text descriptions. |
Haiper AI | Video Creation | Enables creative video generation for educational and promotional content. |
Harness AI to compose and innovate in music production:
AI Tool | Application | Description |
---|---|---|
Suno.ai | Music Generation | Create original music compositions using AI, accessible to creators of all backgrounds. |
Google Magenta | Music & Art Innovation | Explores the intersection of AI and creativity in music and art. |
Google Labs Music FX | Music Effects & Tools | Offers experimental tools to enhance creative musical expression using AI. |
Leverage state-of-the-art voice technologies for realistic audio production:
AI Tool | Application | Description |
---|---|---|
ElevenLabs | Voice Cloning & Synthesis | Advanced voice cloning and synthesis for lifelike audio production, perfect for accessibility and multimedia. |
For additional support or inquiries, please contact research-computing@ucr.edu.