Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon May 9, 2024 • 12
AI PC: Text Generation Text generation LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. OpenVINO/Mixtral-8x7B-Instruct-v0.1-int8-ov Text Generation • Updated Nov 5, 2024 • 135 • 4 OpenVINO/mixtral-8x7b-instruct-v0.1-int4-ov Text Generation • Updated Nov 5, 2024 • 76 • 4 OpenVINO/phi-2-fp16-ov Text Generation • Updated Nov 5, 2024 • 141 • 1 OpenVINO/phi-2-int8-ov Text Generation • Updated Oct 29, 2024 • 52
AI PC: Audio Classification Audio Classification models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. MIT/ast-finetuned-speech-commands-v2 Audio Classification • 0.1B • Updated Sep 10, 2023 • 5.98k • 17 superb/wav2vec2-base-superb-sid Audio Classification • Updated Nov 4, 2021 • 4.1k • 21 anton-l/wav2vec2-base-superb-sv Audio Classification • Updated Nov 11, 2022 • 267 • 3 anton-l/wav2vec2-base-superb-sd Updated Dec 14, 2021 • 444
AI PC: Feature Extraction NLP models for Feature Extraction that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. BAAI/bge-base-en-v1.5 Feature Extraction • 0.1B • Updated Feb 21, 2024 • 4.21M • • 314 BAAI/bge-large-en-v1.5 Feature Extraction • 0.3B • Updated Feb 21, 2024 • 2.77M • • 533 Contrastive-Tension/BERT-Large-CT-STSb Feature Extraction • Updated May 18, 2021 • 71 DeepPavlov/bert-base-cased-conversational Feature Extraction • Updated Nov 8, 2021 • 1.03k • • 8
AI PC: Image-to-Text Image-to-text models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. google/pix2struct-base Image-to-Text • 0.3B • Updated Dec 24, 2023 • 5.89k • 75 microsoft/trocr-base-handwritten Image-to-Text • 0.3B • Updated Feb 11 • 186k • 414
AI PC: Question Answering LLMs for Question Answering that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. aware-ai/roberta-large-squadv2 Question Answering • Updated May 20, 2021 • 42 deepset/bert-base-cased-squad2 Question Answering • 0.1B • Updated Sep 24, 2024 • 25.7k • 20 deepset/roberta-base-squad2 Question Answering • 0.1B • Updated Sep 24, 2024 • 1.4M • • 885 distilbert/distilbert-base-uncased-distilled-squad Question Answering • 0.1B • Updated May 6, 2024 • 132k • • 116
distilbert/distilbert-base-uncased-distilled-squad Question Answering • 0.1B • Updated May 6, 2024 • 132k • • 116
AI PC: Text2Text Generation Text2Text Generation LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. facebook/blenderbot-400M-distill Text2Text Generation • Updated Mar 30, 2023 • 66.6k • 440 facebook/m2m100_418M Text2Text Generation • Updated Feb 29, 2024 • 414k • 303 facebook/mbart-large-50-many-to-one-mmt Text2Text Generation • Updated Mar 28, 2023 • 16.4k • 67 google/mt5-base Text2Text Generation • Updated Jan 24, 2023 • 64.2k • 241
AI PC: Translation LLMs for translation tasks that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. google-t5/t5-base Translation • 0.2B • Updated Feb 14, 2024 • 2.85M • • 725 google-t5/t5-large Translation • 0.7B • Updated Apr 6, 2023 • 377k • • 210 google-t5/t5-small Translation • 0.1B • Updated Jun 30, 2023 • 3.04M • • 464
Intel Neural Chat Fine-tuned 7B parameter LLM models, one of which made it to the top of the 7B HF LLM Leaderboard Intel/neural-chat-7b-v3-3 Text Generation • 7B • Updated Nov 11, 2024 • 48.9k • • 78 Intel/neural-chat-7b-v3-1 Text Generation • 7B • Updated Sep 9, 2024 • 4.82k • 544 Intel/neural-chat-7b-v3 Text Generation • 7B • Updated Nov 14, 2024 • 53 • 67 Intel/neural-chat-7b-v3-2 Text Generation • Updated Feb 22, 2024 • 1.11k • 57
Mistral Models derived from Mistral Intel/Mistral-7B-v0.1-int4-inc Text Generation • 1B • Updated May 31, 2024 • 294 • 4
GPT Series of GPT fine-tuned models Intel/gpt-j-6B-int8-dynamic-inc Text Generation • Updated Apr 19, 2023 • 62 • 16 Intel/gpt-j-6B-int8-static-inc Text Generation • Updated Apr 19, 2023 • 88 • 9 Intel/gpt-j-6B-pytorch-int8-static-inc Text Generation • Updated Jan 18, 2024 • 19 Intel/gpt-j-6b-sparse Text Generation • Updated Dec 7, 2023 • 25 • 1
BGE Intel/bge-large-en-v1.5-rag-int8-static Feature Extraction • Updated Feb 19, 2024 • 38 • 1 Intel/bge-base-en-v1.5-rag-int8-static Feature Extraction • Updated Feb 19, 2024 • 18 Intel/bge-small-en-v1.5-rag-int8-static Feature Extraction • Updated Feb 19, 2024 • 45 • 1
BERT BERT models of varying flavors Intel/bert-base-cased-finetuned-sst2-int8-inc Text Classification • Updated Mar 21, 2024 • 30 Intel/bert-base-uncased-CoLA-int8-inc Text Classification • Updated Mar 22, 2024 • 52 Intel/bert-base-uncased-QNLI-int8-inc Text Classification • Updated Mar 22, 2024 • 34 Intel/bert-base-uncased-STS-B-int8-inc Text Classification • Updated Mar 22, 2024 • 18
ALBERT Quantized versions of ALBERT models for language tasks Intel/albert-base-v2-MRPC-int8-inc Text Classification • Updated Mar 22, 2024 • 18 Intel/albert-base-v2-sst2-int8-dynamic-inc Text Classification • Updated Jun 27, 2023 • 27 Intel/albert-base-v2-sst2-int8-static-inc Text Classification • Updated Mar 22, 2024 • 92
CamemBERT Based on Metas's RoBERTa model released in 2019, trained on 138GB of French text. Intel/camembert-base-mrpc Text Classification • Updated Dec 5, 2022 • 46 Intel/camembert-base-mrpc-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 25
TinyBERT Question Answering model, trained on the SQuAD 1.1 dataset Intel/dynamic_tinybert Question Answering • Updated Mar 22, 2024 • 2.19k • • 80
BART Adaptations on Meta's BART model Intel/bart-large-mrpc Text Classification • Updated Oct 9, 2023 • 29 Intel/bart-large-mrpc-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 25 Intel/bart-large-cnn-int8-dynamic-inc Text2Text Generation • Updated Mar 22, 2024 • 25 • 1
NQ Natural Questions Intel/nq_fid_lfqa_early_exit Updated Oct 29, 2023 • 9 Intel/nq_fid_lfqa Updated Oct 29, 2023 • 7
Electra Intel/electra-small-discriminator-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 27
Intel/electra-small-discriminator-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 27
ViT Originally from Google, Vision Transformer (ViT) Intel/vit-base-patch16-224-int8-static-inc Image Classification • Updated Sep 6, 2022 • 145 • 1
AI PC: Text-to-Image Text-to-image models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. OpenVINO/stable-diffusion-v1-5-fp16-ov Updated Feb 11 • 2 OpenVINO/stable-diffusion-v1-5-int8-ov Updated Feb 11 • 4 OpenVINO/LCM_Dreamshaper_v7-fp16-ov Updated Feb 11 • 3 OpenVINO/LCM_Dreamshaper_v7-int8-ov Updated Feb 11 • 3
AI PC: Automatic Speech Recognition Automatic Speech Recognition models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. openai/whisper-small Automatic Speech Recognition • 0.2B • Updated Feb 29, 2024 • 1.29M • 403 distil-whisper/distil-medium.en Automatic Speech Recognition • 0.4B • Updated Mar 25, 2024 • 90k • 122 facebook/hubert-large-ls960-ft Automatic Speech Recognition • Updated May 24, 2022 • 1.32M • 68 openai/whisper-base Automatic Speech Recognition • 0.1B • Updated Feb 29, 2024 • 687k • 223
distil-whisper/distil-medium.en Automatic Speech Recognition • 0.4B • Updated Mar 25, 2024 • 90k • 122
AI PC: Image Classification Image Classification models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. apple/mobilevit-xx-small Image Classification • Updated Feb 24 • 7.72k • • 16 facebook/convnext-base-224 Image Classification • Updated Jun 13, 2023 • 4.38k • • 9 facebook/levit-256 Image Classification • Updated Jun 1, 2022 • 67 google/mobilenet_v1_1.0_224 Image Classification • Updated May 16, 2023 • 1.35k • 1
AI PC: Masked Language Models Masked language models (MLMs) that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. FacebookAI/roberta-base Fill-Mask • 0.1B • Updated Feb 19, 2024 • 6.38M • • 503 FacebookAI/roberta-large Fill-Mask • 0.4B • Updated Feb 19, 2024 • 16M • 229 FacebookAI/xlm-clm-ende-1024 Fill-Mask • 0.2B • Updated Apr 6, 2023 • 91 FacebookAI/xlm-roberta-base Fill-Mask • 0.3B • Updated Feb 19, 2024 • 13.8M • • 692
AI PC: Text Classification Text Classification LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. Alireza1044/albert-base-v2-sst2 Text Classification • Updated Jul 26, 2021 • 82 BAAI/bge-reranker-base Text Classification • 0.3B • Updated Jun 24, 2024 • 1.01M • 192 ChrisZeng/electra-large-discriminator-nli-efl-tweeteval Text Classification • Updated Apr 20, 2022 • 27 DeepPavlov/xlm-roberta-large-en-ru-mnli Text Classification • Updated Nov 15, 2021 • 99 • 2
ChrisZeng/electra-large-discriminator-nli-efl-tweeteval Text Classification • Updated Apr 20, 2022 • 27
AI PC: Token Classification Token Classification LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. FacebookAI/xlm-roberta-large-finetuned-conll03-english Token Classification • 0.6B • Updated Feb 19, 2024 • 126k • • 173 Jean-Baptiste/roberta-large-ner-english Token Classification • 0.4B • Updated Mar 22, 2023 • 100k • • 71 dslim/bert-base-NER Token Classification • 0.1B • Updated Oct 8, 2024 • 2.03M • • 612 dslim/bert-large-NER Token Classification • 0.3B • Updated Oct 8, 2024 • 113k • • 153
FacebookAI/xlm-roberta-large-finetuned-conll03-english Token Classification • 0.6B • Updated Feb 19, 2024 • 126k • • 173
Jean-Baptiste/roberta-large-ner-english Token Classification • 0.4B • Updated Mar 22, 2023 • 100k • • 71
DPT 3.1 DPT 3.1 (MiDaS) models, leveraging state-of-the-art vision backbones such as BEiT and Swinv2 MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation Paper • 2307.14460 • Published Jul 26, 2023 • 9 Intel/dpt-beit-large-512 Depth Estimation • 0.3B • Updated Jun 21, 2024 • 1.91k • 8 Intel/dpt-beit-large-384 Depth Estimation • 0.3B • Updated Jun 21, 2024 • 134 Intel/dpt-beit-base-384 Depth Estimation • 0.1B • Updated Dec 11, 2023 • 6.96k • 1
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation Paper • 2307.14460 • Published Jul 26, 2023 • 9
Whisper Whisper models for automatic speech recognition (ASR) and speech translation, quantized for faster inference speeds. Intel/whisper-base-int8-dynamic-inc Automatic Speech Recognition • Updated Aug 25, 2023 • 9 • 1 Intel/whisper-base-int8-static-inc Automatic Speech Recognition • Updated Aug 25, 2023 • 9 Intel/whisper-base-onnx-int4-inc Automatic Speech Recognition • Updated Oct 16, 2023 • 20 • 9 Intel/whisper-large-int8-dynamic-inc Automatic Speech Recognition • Updated May 18, 2023 • 25 • 1
Stable Diffusion Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Paper • 2205.11487 • Published May 23, 2022 • 1 Intel/sd-reference-only Updated Feb 9, 2024 • 1 Intel/sd-1.5-square-quantized Updated Aug 29, 2024 • 4 Intel/sd-1.5-lcm-openvino Text-to-Image • Updated Jul 12, 2024 • 2.31k • 3
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Paper • 2205.11487 • Published May 23, 2022 • 1
DPT 3.0 DPT 3.0 (MiDaS) models, leveraging ViT and ViT-hybrid backbones Vision Transformers for Dense Prediction Paper • 2103.13413 • Published Mar 24, 2021 • 1 Intel/dpt-large Depth Estimation • 0.3B • Updated Feb 24, 2024 • 440k • 192 Intel/dpt-hybrid-midas Depth Estimation • Updated Feb 9, 2024 • 241k • 96 Intel/dpt-large-ade Image Segmentation • Updated Mar 25, 2024 • 1.87k • • 10
TVP Text-Visual Prompting Intel/tvp-base Updated Mar 29, 2024 • 73 • 1 Intel/tvp-base-ANet Updated Nov 9, 2023 • 19
LDM3D-VR Suite of diffusion models targeting virtual reality development LDM3D-VR: Latent Diffusion Model for 3D VR Paper • 2311.03226 • Published Nov 6, 2023 • 11 Intel/ldm3d-pano Text-to-3D • Updated Mar 11, 2024 • 132 • 55 Intel/ldm3d-4c Text-to-3D • Updated Mar 1, 2024 • 1.37k • 39 Intel/ldm3d Text-to-3D • Updated Mar 1, 2024 • 236 • 56
DistilBERT Smaller BERT models for question answering and text classification Intel/distilbert-base-cased-distilled-squad-int8-static-inc Question Answering • Updated Mar 21, 2024 • 32 Intel/distilbert-base-uncased-MRPC-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 83 • 1 Intel/distilbert-base-uncased-MRPC-int8-static-inc Text Classification • Updated Mar 22, 2024 • 16 Intel/distilbert-base-uncased-distilled-squad-int8-static-inc Question Answering • Updated Mar 29, 2024 • 1.41k • 5
Intel/distilbert-base-cased-distilled-squad-int8-static-inc Question Answering • Updated Mar 21, 2024 • 32
Intel/distilbert-base-uncased-MRPC-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 83 • 1
Intel/distilbert-base-uncased-distilled-squad-int8-static-inc Question Answering • Updated Mar 29, 2024 • 1.41k • 5
RoBERTa Intel/roberta-base-mrpc Text Classification • Updated Dec 5, 2022 • 28 • 1 Intel/roberta-base-mrpc-int8-dynamic-inc Text Classification • Updated Dec 28, 2022 • 20 Intel/roberta-base-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 46 Intel/roberta-base-squad2-int8-static-inc Updated Mar 21, 2024 • 46 • 1
DeBERTa DeBERTa is a language model that originates from Meta's RoBERTa model with disentangled attention and enhanced mask decoder. Intel/deberta-v3-base-mrpc Text Classification • Updated May 5, 2023 • 30 Intel/deberta-v3-base-mrpc-int8-dynamic-inc Text Classification • Updated Jun 27, 2023 • 17 Intel/deberta-v3-base-mrpc-int8-static-inc Text Classification • Updated May 25, 2023 • 19
ColBERT Text retrieval model, trained on the Natural Questions dataset Intel/ColBERT-NQ Updated Mar 29, 2024 • 20 • 8 google-research-datasets/natural_questions Viewer • Updated Mar 11, 2024 • 26.3k • 10.3k • 103
MiniLM Fine-tuned version of Microsoft's MiniLM models, trained on the GLUE MRPC dataset. Intel/MiniLM-L12-H384-uncased-mrpc Text Classification • Updated Jun 10, 2022 • 22 • 1 Intel/MiniLM-L12-H384-uncased-mrpc-int8-dynamic-inc Text Classification • Updated Dec 28, 2022 • 22 Intel/MiniLM-L12-H384-uncased-mrpc-int8-qat-inc Text Classification • Updated Oct 6, 2023 • 21 Intel/MiniLM-L12-H384-uncased-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 23
DistilBART Intel/distilbart-cnn-12-6-int8-dynamic-inc Text2Text Generation • Updated Mar 22, 2024 • 111 • 2
MS MARCO Large scale information retrieval corpus that was created based on real user search queries using Bing search engine Intel/msmarco_fid_early_exit Updated Oct 29, 2023 • 11 Intel/msmarco_fid Updated Oct 29, 2023 • 11
T5 Originally from Google: Text-To-Text Transfer Transformer (T5) Intel/t5-small-finetuned-cnn-news-int8-dynamic-inc Text2Text Generation • Updated Oct 6, 2023 • 25 Intel/t5-large-finetuned-xsum-cnn-int8-dynamic-inc Text2Text Generation • Updated Mar 21, 2024 • 65 Intel/t5-base-cnn-dm-int8-dynamic-inc Text2Text Generation • Updated Mar 21, 2024 • 23 Intel/t5-small-xsum-int8-dynamic-inc Text2Text Generation • Updated Mar 21, 2024 • 1.37k • 1
XLNet Original paper: XLNet: Generalized Autoregressive Pretraining for Language Understanding Intel/xlnet-base-cased-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 34 Intel/xlnet-base-cased-mrpc Text Classification • Updated Apr 21, 2022 • 47 • 1
LDM3D collection This collection contains the models, papers, and demo associated with the LDM3D release. Intel/ldm3d Text-to-3D • Updated Mar 1, 2024 • 236 • 56 Intel/ldm3d-sr Text-to-3D • Updated Apr 25, 2024 • 11 • 10 Intel/ldm3d-pano Text-to-3D • Updated Mar 11, 2024 • 132 • 55 Intel/ldm3d-4c Text-to-3D • Updated Mar 1, 2024 • 1.37k • 39
AI PC: Text Generation Text generation LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. OpenVINO/Mixtral-8x7B-Instruct-v0.1-int8-ov Text Generation • Updated Nov 5, 2024 • 135 • 4 OpenVINO/mixtral-8x7b-instruct-v0.1-int4-ov Text Generation • Updated Nov 5, 2024 • 76 • 4 OpenVINO/phi-2-fp16-ov Text Generation • Updated Nov 5, 2024 • 141 • 1 OpenVINO/phi-2-int8-ov Text Generation • Updated Oct 29, 2024 • 52
AI PC: Text-to-Image Text-to-image models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. OpenVINO/stable-diffusion-v1-5-fp16-ov Updated Feb 11 • 2 OpenVINO/stable-diffusion-v1-5-int8-ov Updated Feb 11 • 4 OpenVINO/LCM_Dreamshaper_v7-fp16-ov Updated Feb 11 • 3 OpenVINO/LCM_Dreamshaper_v7-int8-ov Updated Feb 11 • 3
AI PC: Audio Classification Audio Classification models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. MIT/ast-finetuned-speech-commands-v2 Audio Classification • 0.1B • Updated Sep 10, 2023 • 5.98k • 17 superb/wav2vec2-base-superb-sid Audio Classification • Updated Nov 4, 2021 • 4.1k • 21 anton-l/wav2vec2-base-superb-sv Audio Classification • Updated Nov 11, 2022 • 267 • 3 anton-l/wav2vec2-base-superb-sd Updated Dec 14, 2021 • 444
AI PC: Automatic Speech Recognition Automatic Speech Recognition models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. openai/whisper-small Automatic Speech Recognition • 0.2B • Updated Feb 29, 2024 • 1.29M • 403 distil-whisper/distil-medium.en Automatic Speech Recognition • 0.4B • Updated Mar 25, 2024 • 90k • 122 facebook/hubert-large-ls960-ft Automatic Speech Recognition • Updated May 24, 2022 • 1.32M • 68 openai/whisper-base Automatic Speech Recognition • 0.1B • Updated Feb 29, 2024 • 687k • 223
distil-whisper/distil-medium.en Automatic Speech Recognition • 0.4B • Updated Mar 25, 2024 • 90k • 122
AI PC: Feature Extraction NLP models for Feature Extraction that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. BAAI/bge-base-en-v1.5 Feature Extraction • 0.1B • Updated Feb 21, 2024 • 4.21M • • 314 BAAI/bge-large-en-v1.5 Feature Extraction • 0.3B • Updated Feb 21, 2024 • 2.77M • • 533 Contrastive-Tension/BERT-Large-CT-STSb Feature Extraction • Updated May 18, 2021 • 71 DeepPavlov/bert-base-cased-conversational Feature Extraction • Updated Nov 8, 2021 • 1.03k • • 8
AI PC: Image Classification Image Classification models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. apple/mobilevit-xx-small Image Classification • Updated Feb 24 • 7.72k • • 16 facebook/convnext-base-224 Image Classification • Updated Jun 13, 2023 • 4.38k • • 9 facebook/levit-256 Image Classification • Updated Jun 1, 2022 • 67 google/mobilenet_v1_1.0_224 Image Classification • Updated May 16, 2023 • 1.35k • 1
AI PC: Image-to-Text Image-to-text models that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. google/pix2struct-base Image-to-Text • 0.3B • Updated Dec 24, 2023 • 5.89k • 75 microsoft/trocr-base-handwritten Image-to-Text • 0.3B • Updated Feb 11 • 186k • 414
AI PC: Masked Language Models Masked language models (MLMs) that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. FacebookAI/roberta-base Fill-Mask • 0.1B • Updated Feb 19, 2024 • 6.38M • • 503 FacebookAI/roberta-large Fill-Mask • 0.4B • Updated Feb 19, 2024 • 16M • 229 FacebookAI/xlm-clm-ende-1024 Fill-Mask • 0.2B • Updated Apr 6, 2023 • 91 FacebookAI/xlm-roberta-base Fill-Mask • 0.3B • Updated Feb 19, 2024 • 13.8M • • 692
AI PC: Question Answering LLMs for Question Answering that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. aware-ai/roberta-large-squadv2 Question Answering • Updated May 20, 2021 • 42 deepset/bert-base-cased-squad2 Question Answering • 0.1B • Updated Sep 24, 2024 • 25.7k • 20 deepset/roberta-base-squad2 Question Answering • 0.1B • Updated Sep 24, 2024 • 1.4M • • 885 distilbert/distilbert-base-uncased-distilled-squad Question Answering • 0.1B • Updated May 6, 2024 • 132k • • 116
distilbert/distilbert-base-uncased-distilled-squad Question Answering • 0.1B • Updated May 6, 2024 • 132k • • 116
AI PC: Text Classification Text Classification LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. Alireza1044/albert-base-v2-sst2 Text Classification • Updated Jul 26, 2021 • 82 BAAI/bge-reranker-base Text Classification • 0.3B • Updated Jun 24, 2024 • 1.01M • 192 ChrisZeng/electra-large-discriminator-nli-efl-tweeteval Text Classification • Updated Apr 20, 2022 • 27 DeepPavlov/xlm-roberta-large-en-ru-mnli Text Classification • Updated Nov 15, 2021 • 99 • 2
ChrisZeng/electra-large-discriminator-nli-efl-tweeteval Text Classification • Updated Apr 20, 2022 • 27
AI PC: Text2Text Generation Text2Text Generation LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. facebook/blenderbot-400M-distill Text2Text Generation • Updated Mar 30, 2023 • 66.6k • 440 facebook/m2m100_418M Text2Text Generation • Updated Feb 29, 2024 • 414k • 303 facebook/mbart-large-50-many-to-one-mmt Text2Text Generation • Updated Mar 28, 2023 • 16.4k • 67 google/mt5-base Text2Text Generation • Updated Jan 24, 2023 • 64.2k • 241
AI PC: Token Classification Token Classification LLMs that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. FacebookAI/xlm-roberta-large-finetuned-conll03-english Token Classification • 0.6B • Updated Feb 19, 2024 • 126k • • 173 Jean-Baptiste/roberta-large-ner-english Token Classification • 0.4B • Updated Mar 22, 2023 • 100k • • 71 dslim/bert-base-NER Token Classification • 0.1B • Updated Oct 8, 2024 • 2.03M • • 612 dslim/bert-large-NER Token Classification • 0.3B • Updated Oct 8, 2024 • 113k • • 153
FacebookAI/xlm-roberta-large-finetuned-conll03-english Token Classification • 0.6B • Updated Feb 19, 2024 • 126k • • 173
Jean-Baptiste/roberta-large-ner-english Token Classification • 0.4B • Updated Mar 22, 2023 • 100k • • 71
AI PC: Translation LLMs for translation tasks that have been validated to run on the AI PC Intel® Core™ Ultra CPU and iGPU. google-t5/t5-base Translation • 0.2B • Updated Feb 14, 2024 • 2.85M • • 725 google-t5/t5-large Translation • 0.7B • Updated Apr 6, 2023 • 377k • • 210 google-t5/t5-small Translation • 0.1B • Updated Jun 30, 2023 • 3.04M • • 464
DPT 3.1 DPT 3.1 (MiDaS) models, leveraging state-of-the-art vision backbones such as BEiT and Swinv2 MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation Paper • 2307.14460 • Published Jul 26, 2023 • 9 Intel/dpt-beit-large-512 Depth Estimation • 0.3B • Updated Jun 21, 2024 • 1.91k • 8 Intel/dpt-beit-large-384 Depth Estimation • 0.3B • Updated Jun 21, 2024 • 134 Intel/dpt-beit-base-384 Depth Estimation • 0.1B • Updated Dec 11, 2023 • 6.96k • 1
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation Paper • 2307.14460 • Published Jul 26, 2023 • 9
Intel Neural Chat Fine-tuned 7B parameter LLM models, one of which made it to the top of the 7B HF LLM Leaderboard Intel/neural-chat-7b-v3-3 Text Generation • 7B • Updated Nov 11, 2024 • 48.9k • • 78 Intel/neural-chat-7b-v3-1 Text Generation • 7B • Updated Sep 9, 2024 • 4.82k • 544 Intel/neural-chat-7b-v3 Text Generation • 7B • Updated Nov 14, 2024 • 53 • 67 Intel/neural-chat-7b-v3-2 Text Generation • Updated Feb 22, 2024 • 1.11k • 57
Whisper Whisper models for automatic speech recognition (ASR) and speech translation, quantized for faster inference speeds. Intel/whisper-base-int8-dynamic-inc Automatic Speech Recognition • Updated Aug 25, 2023 • 9 • 1 Intel/whisper-base-int8-static-inc Automatic Speech Recognition • Updated Aug 25, 2023 • 9 Intel/whisper-base-onnx-int4-inc Automatic Speech Recognition • Updated Oct 16, 2023 • 20 • 9 Intel/whisper-large-int8-dynamic-inc Automatic Speech Recognition • Updated May 18, 2023 • 25 • 1
Mistral Models derived from Mistral Intel/Mistral-7B-v0.1-int4-inc Text Generation • 1B • Updated May 31, 2024 • 294 • 4
Stable Diffusion Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Paper • 2205.11487 • Published May 23, 2022 • 1 Intel/sd-reference-only Updated Feb 9, 2024 • 1 Intel/sd-1.5-square-quantized Updated Aug 29, 2024 • 4 Intel/sd-1.5-lcm-openvino Text-to-Image • Updated Jul 12, 2024 • 2.31k • 3
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Paper • 2205.11487 • Published May 23, 2022 • 1
GPT Series of GPT fine-tuned models Intel/gpt-j-6B-int8-dynamic-inc Text Generation • Updated Apr 19, 2023 • 62 • 16 Intel/gpt-j-6B-int8-static-inc Text Generation • Updated Apr 19, 2023 • 88 • 9 Intel/gpt-j-6B-pytorch-int8-static-inc Text Generation • Updated Jan 18, 2024 • 19 Intel/gpt-j-6b-sparse Text Generation • Updated Dec 7, 2023 • 25 • 1
DPT 3.0 DPT 3.0 (MiDaS) models, leveraging ViT and ViT-hybrid backbones Vision Transformers for Dense Prediction Paper • 2103.13413 • Published Mar 24, 2021 • 1 Intel/dpt-large Depth Estimation • 0.3B • Updated Feb 24, 2024 • 440k • 192 Intel/dpt-hybrid-midas Depth Estimation • Updated Feb 9, 2024 • 241k • 96 Intel/dpt-large-ade Image Segmentation • Updated Mar 25, 2024 • 1.87k • • 10
BGE Intel/bge-large-en-v1.5-rag-int8-static Feature Extraction • Updated Feb 19, 2024 • 38 • 1 Intel/bge-base-en-v1.5-rag-int8-static Feature Extraction • Updated Feb 19, 2024 • 18 Intel/bge-small-en-v1.5-rag-int8-static Feature Extraction • Updated Feb 19, 2024 • 45 • 1
TVP Text-Visual Prompting Intel/tvp-base Updated Mar 29, 2024 • 73 • 1 Intel/tvp-base-ANet Updated Nov 9, 2023 • 19
LDM3D-VR Suite of diffusion models targeting virtual reality development LDM3D-VR: Latent Diffusion Model for 3D VR Paper • 2311.03226 • Published Nov 6, 2023 • 11 Intel/ldm3d-pano Text-to-3D • Updated Mar 11, 2024 • 132 • 55 Intel/ldm3d-4c Text-to-3D • Updated Mar 1, 2024 • 1.37k • 39 Intel/ldm3d Text-to-3D • Updated Mar 1, 2024 • 236 • 56
BERT BERT models of varying flavors Intel/bert-base-cased-finetuned-sst2-int8-inc Text Classification • Updated Mar 21, 2024 • 30 Intel/bert-base-uncased-CoLA-int8-inc Text Classification • Updated Mar 22, 2024 • 52 Intel/bert-base-uncased-QNLI-int8-inc Text Classification • Updated Mar 22, 2024 • 34 Intel/bert-base-uncased-STS-B-int8-inc Text Classification • Updated Mar 22, 2024 • 18
DistilBERT Smaller BERT models for question answering and text classification Intel/distilbert-base-cased-distilled-squad-int8-static-inc Question Answering • Updated Mar 21, 2024 • 32 Intel/distilbert-base-uncased-MRPC-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 83 • 1 Intel/distilbert-base-uncased-MRPC-int8-static-inc Text Classification • Updated Mar 22, 2024 • 16 Intel/distilbert-base-uncased-distilled-squad-int8-static-inc Question Answering • Updated Mar 29, 2024 • 1.41k • 5
Intel/distilbert-base-cased-distilled-squad-int8-static-inc Question Answering • Updated Mar 21, 2024 • 32
Intel/distilbert-base-uncased-MRPC-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 83 • 1
Intel/distilbert-base-uncased-distilled-squad-int8-static-inc Question Answering • Updated Mar 29, 2024 • 1.41k • 5
ALBERT Quantized versions of ALBERT models for language tasks Intel/albert-base-v2-MRPC-int8-inc Text Classification • Updated Mar 22, 2024 • 18 Intel/albert-base-v2-sst2-int8-dynamic-inc Text Classification • Updated Jun 27, 2023 • 27 Intel/albert-base-v2-sst2-int8-static-inc Text Classification • Updated Mar 22, 2024 • 92
RoBERTa Intel/roberta-base-mrpc Text Classification • Updated Dec 5, 2022 • 28 • 1 Intel/roberta-base-mrpc-int8-dynamic-inc Text Classification • Updated Dec 28, 2022 • 20 Intel/roberta-base-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 46 Intel/roberta-base-squad2-int8-static-inc Updated Mar 21, 2024 • 46 • 1
CamemBERT Based on Metas's RoBERTa model released in 2019, trained on 138GB of French text. Intel/camembert-base-mrpc Text Classification • Updated Dec 5, 2022 • 46 Intel/camembert-base-mrpc-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 25
DeBERTa DeBERTa is a language model that originates from Meta's RoBERTa model with disentangled attention and enhanced mask decoder. Intel/deberta-v3-base-mrpc Text Classification • Updated May 5, 2023 • 30 Intel/deberta-v3-base-mrpc-int8-dynamic-inc Text Classification • Updated Jun 27, 2023 • 17 Intel/deberta-v3-base-mrpc-int8-static-inc Text Classification • Updated May 25, 2023 • 19
ColBERT Text retrieval model, trained on the Natural Questions dataset Intel/ColBERT-NQ Updated Mar 29, 2024 • 20 • 8 google-research-datasets/natural_questions Viewer • Updated Mar 11, 2024 • 26.3k • 10.3k • 103
TinyBERT Question Answering model, trained on the SQuAD 1.1 dataset Intel/dynamic_tinybert Question Answering • Updated Mar 22, 2024 • 2.19k • • 80
MiniLM Fine-tuned version of Microsoft's MiniLM models, trained on the GLUE MRPC dataset. Intel/MiniLM-L12-H384-uncased-mrpc Text Classification • Updated Jun 10, 2022 • 22 • 1 Intel/MiniLM-L12-H384-uncased-mrpc-int8-dynamic-inc Text Classification • Updated Dec 28, 2022 • 22 Intel/MiniLM-L12-H384-uncased-mrpc-int8-qat-inc Text Classification • Updated Oct 6, 2023 • 21 Intel/MiniLM-L12-H384-uncased-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 23
BART Adaptations on Meta's BART model Intel/bart-large-mrpc Text Classification • Updated Oct 9, 2023 • 29 Intel/bart-large-mrpc-int8-dynamic-inc Text Classification • Updated Mar 21, 2024 • 25 Intel/bart-large-cnn-int8-dynamic-inc Text2Text Generation • Updated Mar 22, 2024 • 25 • 1
DistilBART Intel/distilbart-cnn-12-6-int8-dynamic-inc Text2Text Generation • Updated Mar 22, 2024 • 111 • 2
NQ Natural Questions Intel/nq_fid_lfqa_early_exit Updated Oct 29, 2023 • 9 Intel/nq_fid_lfqa Updated Oct 29, 2023 • 7
MS MARCO Large scale information retrieval corpus that was created based on real user search queries using Bing search engine Intel/msmarco_fid_early_exit Updated Oct 29, 2023 • 11 Intel/msmarco_fid Updated Oct 29, 2023 • 11
T5 Originally from Google: Text-To-Text Transfer Transformer (T5) Intel/t5-small-finetuned-cnn-news-int8-dynamic-inc Text2Text Generation • Updated Oct 6, 2023 • 25 Intel/t5-large-finetuned-xsum-cnn-int8-dynamic-inc Text2Text Generation • Updated Mar 21, 2024 • 65 Intel/t5-base-cnn-dm-int8-dynamic-inc Text2Text Generation • Updated Mar 21, 2024 • 23 Intel/t5-small-xsum-int8-dynamic-inc Text2Text Generation • Updated Mar 21, 2024 • 1.37k • 1
Electra Intel/electra-small-discriminator-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 27
Intel/electra-small-discriminator-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 27
XLNet Original paper: XLNet: Generalized Autoregressive Pretraining for Language Understanding Intel/xlnet-base-cased-mrpc-int8-static-inc Text Classification • Updated Mar 21, 2024 • 34 Intel/xlnet-base-cased-mrpc Text Classification • Updated Apr 21, 2022 • 47 • 1
ViT Originally from Google, Vision Transformer (ViT) Intel/vit-base-patch16-224-int8-static-inc Image Classification • Updated Sep 6, 2022 • 145 • 1
LDM3D collection This collection contains the models, papers, and demo associated with the LDM3D release. Intel/ldm3d Text-to-3D • Updated Mar 1, 2024 • 236 • 56 Intel/ldm3d-sr Text-to-3D • Updated Apr 25, 2024 • 11 • 10 Intel/ldm3d-pano Text-to-3D • Updated Mar 11, 2024 • 132 • 55 Intel/ldm3d-4c Text-to-3D • Updated Mar 1, 2024 • 1.37k • 39