Model Details Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.

Meta-Llama-3-70B-Instruct

Meta-Llama-3-8B-Instruct

This is the instruction fine-tuned version of Mixtral-8x22B - the latest and largest mixture of experts large language model (LLM) from Mistral AI. This state of the art machine learning model uses a mixture 8 of experts (MoE) 22b models. During inference 2 experts are selected. This architecture allows large models to be fast and cheap at inference.

Mixtral-8x22B-Instruct-v0.1

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to those leading proprietary models.

WizardLM-2-8x22B

WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger open-source leading models

WizardLM-2-7B

Zephyr 141B-A35B is an instruction-tuned (assistant) version of Mixtral-8x22B. It was fine-tuned on a mix of publicly available, synthetic datasets. It achieves strong performance on chat benchmarks.

zephyr-orpo-141b-A35b-v0.1

Gemma is an open-source model designed by Google. This is Gemma 1.1 7B (IT), an update over the original instruction-tuned Gemma release. Gemma 1.1 was trained using a novel RLHF method, leading to substantial gains on quality, coding capabilities, factuality, instruction following and multi-turn conversation quality.

gemma-1.1-7b-it

DBRX is an open source LLM created by Databricks. It uses mixture-of-experts (MoE) architecture with 132B total parameters of which 36B parameters are active on any input. It outperforms existing open source LLMs like Llama 2 70B and Mixtral-8x7B on standard industry benchmarks for language understanding, programming, math, and logic.

dbrx-instruct

Mixtral is mixture of expert large language model (LLM) from Mistral AI. This is state of the art machine learning model using a mixture 8 of experts (MoE) 7b models. During inference 2 expers are selected. This architecture allows large models to be fast and cheap at inference. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks.

Mixtral-8x7B-Instruct-v0.1

The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.2 generative text model using a variety of publicly available conversation datasets.

Mistral-7B-Instruct-v0.2

LLaMa 2 is a collections of LLMs trained by Meta. This is the 70B chat optimized version. This endpoint has per token pricing.

Llama-2-70b-chat-hf

The Dolphin 2.6 Mixtral 8x7b model is a finetuned version of the Mixtral-8x7b model, trained on a variety of data including coding data, for 3 days on 4 A100 GPUs. It is uncensored and requires trust_remote_code. The model is very obedient and good at coding, but not DPO tuned. The dataset has been filtered for alignment and bias. The model is compliant with user requests and can be used for various purposes such as generating code or engaging in general chat.

dolphin-2.6-mixtral-8x7b

A Mythomax/MLewd_13B-style merge of selected 70B models  A multi-model merge of several  LLaMA2 70B finetunes for roleplaying and creative work. The goal was to create a model that combines creativity with intelligence for an enhanced experience.

lzlv_70b_fp16_hf

OpenChat is a library of open-source language models that have been fine-tuned with C-RLFT, a strategy inspired by offline reinforcement learning. These models can learn from mixed-quality data without preference labels and have achieved exceptional performance comparable to ChatGPT. The developers of OpenChat are dedicated to creating a high-performance, commercially viable, open-source large language model and are continuously making progress towards this goal.

openchat_3.5

LLaVa is a multimodal model that supports vision and language models combined.

llava-1.5-7b-hf

Latest version of the Airoboros model fine-tunned version of llama-2-70b using the Airoboros dataset. This model is currently running jondurbin/airoboros-l2-70b-2.2.1 

airoboros-70b

SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/) specialized for the final denoising steps. Note that the base model can be used as a standalone module.

sdxl

Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. 

Llama-2-7b-chat-hf

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

whisper-large

BGE embedding is a general Embedding Model. It is pre-trained using retromae and trained on large-scale pair data using contrastive learning. Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned

bge-large-en-v1.5

Yi-34B-Chat

This offers the imaginative writing style of chronos while still retaining coherency and being capable. Outputs are long and utilize exceptional prose. Supports a maxium context length of 4096. The model follows the Alpaca prompt format.

chronos-hermes-13b-v2

bge-base-en-v1.5

Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input.

stable-diffusion-v1-4

A named entity recognition model for 10 high-resource languages, trained on a fine-tuned mBERT base model. The model recognizes three types of entities: location, organization, and person. The training data consists of entity-annotated news articles from various datasets for each language, and the model distinguishes between the beginning and continuation of an entity.

bert-base-multilingual-cased-ner-hrl

We present BERTje, a Dutch pre-trained BERT model developed at the University of Groningen. BERTje achieved state-of-the-art results on several NLP tasks such as named entity recognition and part-of-speech tagging. We also provide a detailed comparison of BERTje with other pre-trained models such as mBERT and RobBERT.

bert-base-dutch-cased

MythoMax-L2-13b

A Named Entity Recognition model fine-tuned from CamemBERT on the Wikiner-FR dataset. Our model achieves high performance on various entities, including Persons, Organizations, Locations, and Miscellaneous entities.

camembert-ner

We present a fine-tuned RoBERTa model for English named entity recognition, achieving high performance on both formal and informal datasets. Our approach uses a simplified version of the CONLL2003 dataset and removes unnecessary prefixes for improved efficiency. The resulting model shows superiority over other models, especially on entities that do not begin with uppercase letters, and can be used for various applications such as email signature detection.

roberta-large-ner-english

The National Library of Sweden has released three pre-trained language models based on BERT and ALBERT for Swedish text. The models include a BERT base model, a BERT fine-tuned for named entity recognition, and an experimental ALBERT model. They were trained on approximately 15-20 GB of text data from various sources such as books, news, government publications, Swedish Wikipedia, and internet forums.

bert-base-swedish-cased

DreamShaper started as a model to have an alternative to MidJourney in the open source world. I didn't like how MJ was handled back when I started and how closed it was and still is, as well as the lack of freedom it gives to users compared to SD. Look at all the tools we have now from TIs to LoRA, from ControlNet to Latent Couple. We can do anything. The purpose of DreamShaper has always been to make "a better Stable Diffusion", a model capable of doing everything on its own, to weave dreams.

DreamShaper

Phind-CodeLlama-34B-v2 is an open-source language model that has been fine-tuned on 1.5B tokens of high-quality programming-related data and achieved a pass@1 rate of 73.8% on HumanEval. It is multi-lingual and proficient in Python, C/C++, TypeScript, Java, and more. It has been trained on a proprietary dataset of instruction-answer pairs instead of code completion examples.  The model is instruction-tuned on the Alpaca/Vicuna format to be steerable and easy-to-use. It accepts the Alpaca/Vicuna instruction format and can generate one completion for each prompt.

Phind-CodeLlama-34B-v2

FinBERT is a pre-trained NLP model for financial sentiment analysis, built by fine-tuning the BERT language model on a large financial corpus. The model provides softmax outputs for three labels: positive, negative, or neutral.

finbert

A pre-trained language model developed specifically for protein sequences using a masked language modeling (MLM) objective. It achieved impressive results when fine-tuned on downstream tasks such as secondary structure prediction and sub-cellular localization. The model was trained on uppercase amino acids only and used a vocabulary size of 21, with inputs of the form "[CLS] Protein Sequence A [SEP] Protein Sequence B [SEP]"

prot_bert

A pretrained language model on protein sequences using a masked language modeling objective. It achieved high scores on various downstream tasks such as secondary structure prediction and localization. The model was trained on a large corpus of protein sequences in a self-supervised fashion, without human labeling, using a combination of a Bert model and a vocabulary size of 21.

prot_bert_bfd

The Deliberate Model allows for the creation of anything desired, with the potential for better results as the user's knowledge and detail in the prompt increase. The model is ideal for meticulous anatomy artists, creative prompt writers, art designers, and those seeking explicit content.

Deliberate

The ALBERT model is a transformer-based language model developed by Google researchers, designed for self-supervised learning of language representations. The model uses a combination of masked language modeling and sentence order prediction objectives, trained on a large corpus of English text data. Fine-tuning the model on specific downstream tasks can lead to improved performance, and various pre-trained versions are available for different NLP tasks.

albert-base-v1

The ALBERT model is a variant of BERT that uses a larger model size and more training data to improve performance on downstream NLP tasks. It was trained on a combination of BookCorpus and English Wikipedia, and achieved state-of-the-art results on several benchmark datasets. Fine-tuning ALBERT on specific tasks can further improve its performance.

albert-base-v2

An Arabic pretrained language model based on Google's BERT architecture, with two versions: AraBERTv1 and AraBERTv2. It uses the same BERT-Base configuration and is trained on a large dataset of 200 million words, including OSCAR-unshuffled, Arabic Wikipedia, and Assafir news articles. The model is available in TensorFlow 1.x and Hugging Face models repository.

bert-base-arabertv02

A transformer-based language model developed by Google Research that achieved state-of-the-art results on a wide range of NLP tasks. The model was pre-trained on a large corpus of English text, including BookCorpus and English Wikipedia, using a masked language modeling objective. Fine-tuned versions of the model are available for various downstream tasks, and the model has been shown to achieve excellent results on tasks such as question answering, sentiment analysis, and named entity recognition.

bert-base-cased

A pre-trained language model developed by the HuggingFace team for the Chinese language. It uses a fill-mask approach and has been trained on a large corpus of Chinese text data. The model can be used for various natural language processing tasks such as masked language modeling and has been shown to achieve state-of-the-art results in certain benchmarks. However, like other language models, it also comes with risks, limitations, and biases, including perpetuating harmful stereotypes and biases present in the data it was trained on. Users are advised to carefully evaluate and mitigate these risks when using the model.

bert-base-chinese

A pre-trained language model developed using Google's TensorFlow code and trained on a single cloud TPU v2. The model was trained for 810k steps with a batch size of 1024 and sequence length of 128, and then fine-tuned for 30k steps with sequence length of 512. The authors used a variety of data sources, including German Wikipedia, OpenLegalData, and news articles, and employed spacy v2.1 for data cleaning and segmentation. The model achieved good performance on various downstream tasks, such as germEval18Fine, germEval18coarse, germEval14, CONLL03, and 10kGNAD, without extensive hyperparameter tuning. Additionally, the authors found that even a randomly initialized BERT can achieve good performance when trained exclusively on labeled downstream datasets.

bert-base-german-cased

A pre-trained multilingual model that uses a masked language modeling objective to learn a bidirectional representation of languages. It was trained on 104 languages with the largest Wikipedias, and its inputs are in the form of [CLS] Sentence A [SEP] Sentence B [SEP]. The model is primarily aimed at being fine-tuned on tasks that use the whole sentence, potentially masked, to make decisions.

bert-base-multilingual-cased

A transformer-based language model trained on 102 languages with the largest Wikipedia. It was introduced in a research paper by Google Research and has been widely used for various natural language processing tasks. The model is trained using a masked language modeling objective, where 15% of the tokens are masked, and the model predicts the missing tokens.

bert-base-multilingual-uncased

A transformers model pretrained on a large corpus of English data in a self-supervised fashion. It was trained on BookCorpus, a dataset consisting of 11,038 unpublished books, and English Wikipedia, excluding lists, tables, and headers. The model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks.

bert-base-uncased

A transformer-based language model pre-trained on a large corpus of English data using a masked language modeling objective. It was introduced in a research paper by Google researchers and achieved state-of-the-art results on various natural language processing tasks. The model is cased, meaning it differentiates between English and english, and has a configuration of 24 layers, 1024 hidden dimensions, 16 attention heads, and 336M parameters.

bert-large-cased

BERT is a transformers model pretrained on a large corpus of English data. Supports masked language modeling and next sentence prediction

bert-large-uncased

A whole word masking model finetuned on SQuAD is a transformer-based language model pretrained on a large corpus of English data. The model was trained using a masked language modeling objective, where 15% of the tokens in a sentence were randomly masked, and the model had to predict the missing tokens. The model was also fine-tuned on the SQuAD dataset for question answering tasks, achieving high scores on both F1 and exact match metrics.

bert-large-uncased-whole-word-masking-finetuned-squad

StarCoder2-15B model is a 15B parameter model trained on 600+ programming languages. It specializes in code completion.

starcoder2-15b

We extract contextual embedding features from Camembert, a fill-mask language model, for the task of sentiment analysis. We use the tokenize and encode functions to convert our sentence into a numerical representation, and then feed it into the Camembert model to get the contextual embeddings. We extract the embeddings from all 12 self-attention layers and the input embedding layer to form a 13-dimensional feature vector for each sentence.

camembert-base

A model trained on approximately 58 million tweets and fine-tuned for emotion recognition using the TweetEval benchmark. The model achieves high accuracy on various emotion classification tasks, including emojii, emotion, hate, irony, offensive, sentiment, stance/abortion, stance/atheism, stance/climate, stance/feminist, and stance/hillary.

twitter-roberta-base-emotion

A RoBERTa-base trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis with the TweetEval benchmark. This model is suitable for English.

twitter-roberta-base-sentiment

Code Llama is a state-of-the-art LLM capable of generating code, and natural language about code, from both code and natural language prompts. This particular instance is the 34b instruct variant

CodeLlama-34b-Instruct-hf

CodeLlama-70b is the largest and latest code generation from the Code Llama collection. 

CodeLlama-70b-Instruct-hf

We present a fine-tuned BERT-base uncased model for question answering on the SQuAD v1 dataset. Our model achieves an exact match score of 80.9104 and an F1 score of 88.2302 without any hyperparameter search.

bert-base-uncased-squad-v1

bert-large-cased-finetuned-conll03-english

We present a BERT-based language model called bert-large-uncased-whole-word-masking-squad2, trained on the SQuAD2.0 dataset for extractive question answering. The model achieves high scores on exact match and F1 metrics.

bert-large-uncased-whole-word-masking-squad2

Microsoft's MiniLM-L12-H384-uncased language model achieved state-of-the-art results on the SQuAD 2.0 question-answering benchmark, with exact match and F1 scores of 76.13% and 79.54%, respectively. The model was trained on the SQuAD 2.0 dataset using a batch size of 12, learning rate of 4e-5, and 4 epochs. The authors suggest using their model as a starting point for building large language models for downstream NLP tasks.

minilm-uncased-squad2

A pre-trained language model based on RoBERTa, fine-tuned on the SQuAD2.0 dataset for extractive question answering. It achieved scores of 79.87% exact match and 82.91% F1 score on the SQuAD2.0 dev set. Deepset is the company behind the open-source NLP framework Haystack, and offers other resources such as Distilled roberta-base-squad2, German BERT, and GermanQuAD datasets and models.

roberta-base-squad2

We present a RoBERTa-based question answering model called roberta-base-squad2 for extractive QA on COVID-19 related texts. The model was trained on the SQuAD-style CORD-19 annotations and achieved promising results on 5-fold cross-validation.

roberta-base-squad2-covid

This is the roberta-large model, fine-tuned using the SQuAD2.0 dataset.

roberta-large-squad2

Deepset presents tinyroberta-squad2, a distilled version of their roberta-base-squad2 model that achieves similar performance while being faster. The model is trained on SQuAD 2.0 and uses Haystack's infrastructure with 4x Tesla V100 GPUs. It achieved 78.69% exact match and 81.92% F1 score on the SQuAD 2.0 dev set.

tinyroberta-squad2

The DistilBERT model is a small, fast, cheap, and lightweight Transformer model trained by distilling BERT base. It has 40% fewer parameters than the original BERT model and runs 60% faster, preserving over 95% of BERT's performance. The model was fine-tuned using knowledge distillation on the SQuAD v1.1 dataset and achieved a F1 score of 87.1 on the dev set.

distilbert-base-cased-distilled-squad

The DistilBERT model is a distilled version of the BERT base multilingual model, trained on 104 languages and featuring 6 layers, 768 dimensions, and 12 heads. It is designed for masked language modeling and next sentence prediction tasks, with potential applications in natural language processing and downstream tasks. However, it should not be used to intentionally create hostile or alienating environments for people, and users should be aware of its risks, biases, and limitations.

distilbert-base-multilingual-cased

DistilBERT is a smaller, faster, and cheaper version of BERT, a popular language model. It was trained on the same data as BERT, including BookCorpus and English Wikipedia, but with a few key differences in the preprocessing and training procedures. Despite its smaller size, DistilBERT achieve's similar results to BERT on various natural language processing tasks.

distilbert-base-uncased

DistilBERT is a small, fast, cheap and light Transformer model trained by distilling BERT base. It has 40% less parameters than bert-base-uncased, runs 60% faster while preserving over 95% of BERT's performances as measured on the GLUE language understanding benchmark. This model is a fine-tune checkpoint of DistilBERT-base-uncased, fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1.

distilbert-base-uncased-distilled-squad

DistilBERT-base-uncased-finetuned-sst-2-english achieved an accuracy of 0.91 on the glue dataset, with a loss of 0.39 and an F1 score of 0.91. The model was trained on the sst2 dataset with a configuration of default and a split of train.

distilbert-base-uncased-finetuned-sst-2-english

DistilRoBERTa is a distilled version of the RoBERTa-base model, with 6 layers, 768 dimensions, and 12 heads, totaling 82M parameters. It is trained on OpenWebTextCorpus, a reproduction of OpenAI's WebText dataset, and achieves comparable performance to RoBERTa while being twice as fast. The model is designed for masked language modeling and can be fine-tuned for downstream tasks, but it also comes with potential biases and limitations, including significant gender and ethnicity biases in its predictions.

distilroberta-base

 BioBERT is a pre-trained biomedical language representation model for biomedical text mining based on original BERT and trained by DMIS-LAB

biobert-base-cased-v1.2

The bert-base-NER model is a fine-tuned BERT model that achieves state-of-the-art performance on the CoNLL-2003 Named Entity Recognition task. It was trained on the English version of the standard CoNLL-2003 dataset and recognizes four types of entities: location, organization, person, and miscellaneous. The model occasionally tags subword tokens as entities and post-processing of results may be necessary to handle these cases.

bert-base-NER

bert-base-NER-uncased

A fine-tuned BERT model that achieves state-of-the-art performance on the CoNLL-2003 Named Entity Recognition task. The model was trained on the English version of the standard CoNLL-2003 dataset and distinguishes between four types of entities: location, organization, person, and miscellaneous.

bert-large-NER

The Bio+Clinical BERT model, is initialized from BioBERT and trained on all MIMIC notes. The model was pre-trained using a rules-based section splitter and Sentispacy tokenizer, with a batch size of 32, max sequence length of 128, and learning rate of 5·10^-5 for 150,000 steps.

Bio_ClinicalBERT

The Bio+Discharge Summary BERT model, initialized from BioBERT and trained on only discharge summaries from MIMIC, is described. The model was pre-trained using a rules-based section splitter and SentencePiece tokenizer, with a batch size of 32, maximum sequence length of 128, and learning rate of 5·10^-5 for 150,000 steps.

Bio_Discharge_Summary_BERT

The Vision Transformer (ViT) is a transformer encoder model pre-trained on ImageNet-21k and fine-tuned on ImageNet, achieving state-of-the-art results in image classification. The model presents images as a sequence of fixed-size patches and adds a CLS token for classification tasks. The authors recommend using fine-tuned versions of the model for specific tasks.

vit-base-patch16-224

The Vision Transformer (ViT) model, pre-trained on ImageNet-21k and fine-tuned on ImageNet, achieves state-of-the-art results on image classification tasks. The model uses a transformer encoder architecture and presents images as a sequence of fixed-size patches, adding a [CLS] token for classification tasks. The pre-trained model can be used for downstream tasks such as extracting features and training standard classifiers.

vit-base-patch16-384

Chinese pre-trained BERT with Whole Word Masking, which can be used for various NLP tasks such as question answering, sentiment analysis, named entity recognition, etc. This work is based on the original BERT model but with additional whole word masking techniques to improve its performance on out-of-vocabulary words.

chinese-bert-wwm-ext

We present Chinese pre-trained BERT with Whole Word Masking, which is an extension of the original BERT model tailored for Chinese natural language processing tasks. This variant uses whole word masking instead of subword tokenization to improve performance on out-of-vocabulary words and enhance language understanding capabilities.

chinese-roberta-wwm-ext

CodeBERTa is a RoBERTa-like model trained on the CodeSearchNet dataset from GitHub.  Supported languages: go, java, javascript, php, python, ruby.

CodeBERTa-small-v1

Vision Transformer (ViT) trained for object detection

yolos-base

The YOLOS model, a Vision Transformer (ViT) trained using the DETR loss, achieves 42 AP on COCO validation 2017, similar to DETR and more complex frameworks like Faster R-CNN, despite its small size. The model uses a bipartite matching loss to compare predicted classes and bounding boxes to ground truth annotations. Fine-tuned on COCO 2017 object detection dataset consisting of 118k/5k annotated images for training/validation, it achieved 36.1 AP on validation set.

yolos-small

The YOLOS model, a Vision Transformer (ViT) trained using the DETR loss, achieved an AP of 28.7 on COCO 2017 validation, outperforming other state-of-the-art object detection models while being much simpler. It was pre-trained on ImageNet-1k and fine-tuned on COCO 2017 object detection, a dataset consisting of 118k/5k annotated images for training/validation respectively. The model uses a bipartite matching loss and is trained using standard cross-entropy and a linear combination of the L1 and generalized IoU loss.

yolos-tiny

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Model has 24 layers and 1024 out dim. 

e5-base-v2

e5-large-v2

SecBERT is a pretrained language model for cyber security text, trained on a dataset of papers from various sources, including APTnotes, Stucco-Data, and CASIE. The model has its own wordpiece vocabulary, secvocab, and is available in two versions, SecBERT and SecRoBERTa. The model can improve downstream tasks such as NER, text classification, semantic understanding, and Q&A in the cyber security domain.

SecBERT

The KLUE BERT base is a pre-trained BERT model on Korean Language. It was developed by the Facebook AI Research Lab and is licensed under cc-by-sa-4.0. The model can be used for various tasks like topic classification, semantic textual similarity, natural language inference, named entity recognition, and others.

bert-base

Llama-2-13b-chat-hf

PubMedBERT is a pretrained language model specifically designed for biomedical natural language processing tasks. It was trained from scratch using abstracts and full-text articles from PubMed and PubMedCentral, and achieved state-of-the-art performance on various biomedical NLP tasks.

BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext

The BEiT model is a Vision Transformer (ViT) pre-trained on ImageNet-21k, a dataset of 14 million images and 21,841 classes, using a self-supervised approach. The model was fine-tuned on the same dataset and achieved state-of-the-art performance on various image classification benchmarks. The BEiT model uses relative position embeddings and mean-pools the final hidden states of the patch embeddings for classification.

beit-base-patch16-224-pt22k-ft22k

A pre-trained language model designed to handle both programming languages and natural languages. With a multi-task learning framework that includes masked language modeling, next sentence prediction, and replaced token detection, CodeBERT achieves state-of-the-art results on various code understanding tasks while also performing well on natural language processing benchmarks. We analyze the effects of different design choices and provide insights into the behavior of CodeBERT, demonstrating its potential as a versatile tool for a wide range of applications involving both coding and natural language understanding.

codebert-base-mlm

DeBERTa is a variant of BERT that uses disentangled attention and an enhanced mask decoder to improve performance on natural language understanding (NLU) tasks. In a study, DeBERTa outperformed BERT and RoBERTa on most NLU tasks with only 80GB of training data. The model showed particularly strong results on the SQuAD 1.1/2.0 and MNLI tasks.

deberta-base

DeBERTa (Decoding-Enhanced BERT with Disentangled Attention) is a novel language model that improves upon BERT and RoBERTa using disentangled attention and enhanced mask decoding. It achieves state-of-the-art results on various NLU tasks while requiring less computational resources than its predecessors.

deberta-v2-xlarge

DeBERTaV3 is an improved version of the DeBERTa model that uses ELECTRA-style pre-training with gradient-disentangled embedding sharing. The new model significantly improves performance on downstream tasks compared to DeBERTa, and achieves state-of-the-art results on SQuAD 2.0 and MNLI tasks. DeBERTaV3 has a hidden size of 768 and 86 million backbone parameters, and was trained using a vocabulary of 128K tokens.

deberta-v3-base

Resnet model pre-trained on ImageNet-1k at resolution 224x224 for image classification

resnet-50

The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.

Mistral-7B-Instruct-v0.1

Mixtral-8x22B is the latest and largest mixture of expert large language model (LLM) from Mistral AI. This is state of the art machine learning model using a mixture 8 of experts (MoE) 22b models. During inference 2 expers are selected. This architecture allows large models to be fast and cheap at inference.  This model is not instruction tuned. 

Mixtral-8x22B-v0.1

koelectra-small-v2-distilled-korquad-384

The German BERT model was fine-tuned on the Legal-Entity-Recognition dataset for the named entity recognition (NER) task, achieving an F1 score of 85.67% on the evaluation set. The model uses a pre-trained BERT base model and is trained with a provided script from Hugging Face. The labels covered include various types of legal entities, such as companies, organizations, and individuals.

bert-base-german-finetuned-ler

This paper presents a fine-tuned Spanish BERT model (BETO) for the Named Entity Recognition (NER) task. The model was trained on the CONLL Corpora ES dataset and achieved an F1 score of 90.17%. The authors also compared their model with other state-of-the-art models, including a multilingual BERT and a TinyBERT model, and demonstrated its effectiveness in identifying entities in Spanish text.

Browse deepinfra models:

Category/all