AI Models¶
The UFIT Research Computing AI Support Team maintains a suite of commonly used AI models on HiPerGator. Users may copy these models to their own space, make modifications, and follow the instructions provided to run jobs on HiPerGator. Each model directory includes a README file with additional information.
For assistance with these models or AI-related questions, submit a ticket via UFIT Research Computing Support.
AI Models on HiPerGator¶
| dirpath | dirsize | name | name_url | version | url | license_text | license | license_url | date | categories | description |
|---|---|---|---|---|---|---|---|---|---|---|---|
| /data/ai/models/computer_vision/ultralytics_yolov8 | 605.2 MiB | Ultralytics YOLO | Ultralytics YOLO | v8 | https://github.com/ultralytics/ultralytics | AGPL-3.0 License | AGPL-3.0 License: This OSI-approved open-source license is ideal for students and enthusiasts and Enterprise License: Designed for commercial use | https://github.com/ultralytics/ultralytics?tab=readme-ov-file#license | 5-May-24 | Computer vision | YOLOv8 Detect, Segment and Pose models pretrained on the COCO dataset are available here, as well as YOLOv8 Classify models pretrained on the ImageNet dataset. Track mode is available for all Detect, Segment and Pose models. |
| /data/ai/models/healthcare_life_science/proteinfolding/alphafold | 8.7 GiB | alphafold | alphafold | v2.0.0 | https://github.com/deepmind/alphafold | Apache License 2.0 | Apache License 2.0 | nan | 6-Jul-22 | Healthcare and life science | Predicts protein structures. If you publish research using alphafold, the original paper must be cited. |
| /data/ai/models/healthcare_life_science/proteinfolding/rosettafold | 1.0 GiB | RoseTTAFold | RoseTTAFold | v1.0.0 | https://github.com/RosettaCommons/RoseTTAFold | MIT License | MIT License | https://github.com/RosettaCommons/RoseTTAFold/blob/main/LICENSE | 11-Mar-21 | Healthcare and life science | Predicts protein structures. If you publish research using RoseTTAFold, the original paper must be cited https://www.biorxiv.org/content/10.1101/2021.06.14.448402v |
| /data/ai/models/nvidia/stylegan3 | 7.2 GiB | StyleGAN | StyleGAN | 3 | https://catalog.ngc.nvidia.com/orgs/nvidia/teams/research/models/stylegan3 | Nvidia Source Code License | Nvidia Source Code License | https://github.com/NVlabs/stylegan3/blob/main/LICENSE.txt | 29-Apr-24 | Imaging | StyleGAN3 is a cutting-edge generative model for high-quality image synthesis, offering unparalleled control over image style and content, making it ideal for creative and enterprise applications. |
| /data/ai/models/multimodel/clip/clip-vit-base-patch32 | 3.4 GiB | CLIP | CLIP | openai/clip-vit-base-patch32 | https://huggingface.co/openai/clip-vit-base-patch32 | Apache License 2.0 | Apache License 2.0 | nan | 17-Jul-23 | Multimodal | The clip-vit-base-patch32 uses a ViT-B/32 Transformer architecture as an image encoder and uses a masked self-attention Transformer as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss. |
| /data/ai/models/multimodel/clip/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224 | 1.5 GiB | BiomedCLIP | BiomedCLIP | microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224 | https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224 | MIT License | MIT License | https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md | 17-Jul-23 | Multimodal | BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning. It uses PubMedBERT as the text encoder and Vision Transformer as the image encoder, with domain-specific adaptations. It can perform various vision-language processing (VLP) tasks such as cross-modal retrieval, image classification, and visual question answering. |
| /data/ai/models/nlp/gemma | 250.1 GiB | Gemma | Gemma | nan | https://ai.google.dev/gemma | gemma | gemma | https://ai.google.dev/gemma/terms | 9-Apr-24 | NLP | Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. Developed by Google DeepMind and other teams across Google, Gemma is named after the Latin gemma, meaning "precious stone." |
| /data/ai/models/nlp/llama | 6.7 TiB | Llama | Llama | Llama2, Llama3 | https://llama.meta.com/ | llama | llama | https://llama.meta.com/llama2/license/ | 19-Apr-24 | NLP | LLaMA models are powerful language models developed by Meta AI, with the latest version being LLaMA 3, which significantly improves performance and accessibility for various natural language processing tasks. |
| /data/ai/models/nlp/meditron | 564.2 GiB | Meditron | Meditron | nan | https://github.com/epfLLM/meditron | llama | llama | https://huggingface.co/meta-llama/Llama-2-7b-chat-hf/blob/main/LICENSE.txt | 3-May-24 | NLP | Meditron is a suite of open-source medical Large Language Models (LLMs). The team provide Meditron-7B and Meditron-70B, fine-tuned for medical tasks using a diverse medical dataset. Among these, Meditron-70B shows superior performance compared to other models like Llama-2-70B, GPT-3.5, and Flan-PaLM across multiple medical reasoning tasks. |
| /data/ai/models/nlp/megatron | 22.3 GiB | Megatron-LM | Megatron-LM | 2.2, 2.5, 3.0 | https://github.com/NVIDIA/Megatron-LM | Apache License 2.0 | Apache License 2.0 | https://github.com/NVIDIA/Megatron-LM/blob/main/LICENSE | nan | NLP | Megatron-LM, a fascinating language model developed by the Applied Deep Learning Research team at NVIDIA. |
| /data/ai/models/nlp/mistral_ai | 875.6 GiB | Mistral AI | Mistral AI | nan | https://mistral.ai/ | Apache License 2.0 | Apache License 2.0 | nan | 9-Apr-24 | NLP | Mistral AI offers a variety of language models, including open-weights models like Mistral 7B, Mixtral 8x7B, and Mixtral 8x22B, as well as optimized commercial models such as Mistral Small, Mistral Medium, Mistral Large, and Mistral Embeddings |
| /data/ai/models/nvidia/bionemo/dnabert | 64.3 GiB | DNABERT | DNABERT | 1.2 | https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/dnabert | nan | 0 | nan | 28-Feb-24 | NLP | DNABERT generates a dense representation of a genome sequence by identifying contextually similar sequences in the human genome. DNABert is a DNA sequence model trained on sequences from the human reference genome Hg38.p13. |
| /data/ai/models/nvidia/nemo/nemo_24.01.gemma | 21.4 GiB | Nemo_24.01_Gemma | Nemo_24.01_Gemma | nan | https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo/tags | NVIDIA AI Product Agreement | NVIDIA AI Product Agreement | https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/ | 18-Apr-24 | NLP | NeMo framework container with the pre-trained model Gemma. |
| /data/ai/models/nvidia/nemo/nemo_24.01.starcoder2 | 22.6 GiB | Nemo_24.03_StarCoder2 | Nemo_24.03_StarCoder2 | 2 | https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo/tags | NVIDIA AI Product Agreement | NVIDIA AI Product Agreement | https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/ | 18-Apr-24 | NLP | NeMo framework container with the pre-trained model StarCoder2. |
| /data/ai/models/nvidia/nemo/nemo_24.03.codegemma | 20.2 GiB | Nemo_24.03_CodeGemma | Nemo_24.03_CodeGemma | nan | https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo/tags | NVIDIA AI Product Agreement | NVIDIA AI Product Agreement | https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/ | 18-Apr-24 | NLP | NeMo framework container with the pre-trained model CodeGemma. |
| /data/ai/models/nlp/gatortron | 50.2 GiB | Gatortron | Gatortron | nan | https://huggingface.co/UFNLP | Apache License 2.0 | Apache License 2.0 | nan | 3-May-24 | NLP | GatorTron is a large clinical language model developed by researchers at the University of Florida Health in collaboration with NVIDIA. Its designed to accelerate research and medical decision-making by extracting insights from massive volumes of clinical data with unprecedented speed and clarity. |