This is a Dutch patient simulation model fine-tuned based on Google's Gemma 2 9B model, specifically designed for medical education scenarios. The model always responds in a fixed JSON structure, simulating a patient 'Maria' who has just completed surgery and is in the recovery process, supporting nursing students to exercise communication and clinical reasoning skills in a safe environment.

Natural Language ProcessingGgufOther

An advanced named entity recognition model specifically designed to extract structured information from resumes. This model was trained on 22,542 resume samples, achieving an F1 score of 90.87%. It can recognize 25 types of entities, including personal information, contact details, work experience, educational background, and skills.

Natural Language ProcessingSafetensorsMultiple Languages

Phi-4 Reasoning is a cutting-edge open-weight reasoning model based on Phi-4, fine-tuned with supervised chain-of-thought trajectory datasets and trained via reinforcement learning, specializing in mathematics, science, and programming skills.

Natural Language ProcessingTransformersMultiple Languages

A vision-language-action model specifically designed for Minecraft, capable of executing thousands of in-game skills based on human language commands

MultimodalTransformersEnglish

NVIDIA Isaac GR00T N1 is the world's first open-source foundational model for general humanoid robot reasoning and skills, with a scale of 2 billion parameters.

MultimodalSafetensors

This is a sentence-transformers model specifically trained for job title matching and similarity, fine-tuned on all-mpnet-base-v2 with training data containing numerous job titles and their related skills/requirements.

Natural Language ProcessingSafetensors

en_skillner is a named entity recognition model specifically designed to extract skills, experience, and benefits from recruitment advertisements. This model is built on the spaCy framework and can accurately identify three key types of entities in recruitment texts. Since May 2025, Nesta has stopped further development and maintenance of this model.

Natural Language ProcessingSpacyEnglish

Granite-8B-Code-Instruct-4K is an 8-billion-parameter code instruction model, fine-tuned on various permissible instruction datasets based on Granite-8B-Code-Base-4K, enhancing its ability to follow instructions, including logical reasoning and problem-solving skills.

Natural Language ProcessingTransformersOther

Dolphin 2.9 is an uncensored AI assistant model based on Llama-3-70b, featuring multiple instructions, conversational skills, and programming capabilities, with preliminary support for agent functionality and function calling.

Natural Language ProcessingTransformersEnglish

A storytelling model specifically designed for children aged 6-12, trained on a dataset of over 900,000 children's stories, aimed at fostering creativity, empathy, and language skills.

Natural Language ProcessingTransformersEnglish

This model is created by merging Locutusque/TinyMistral-248M-Instruct and Felladrin/TinyMistral-248M-SFT-v4 using the mergekit tool, combining the strengths of both. It possesses programming capabilities and reasoning skills while maintaining low hallucination and strong instruction-following abilities.

Natural Language ProcessingTransformersEnglish

DistilBERT-based LinkedIn skill recognition model for identifying professional skills from text

Natural Language ProcessingTransformers

ReasTAP is a table reasoning-based pretrained model that injects table reasoning skills through synthetic reasoning examples and is fine-tuned on the WikiSQL dataset.

Natural Language ProcessingTransformersEnglish

ReasTAP is a pre-trained model for table reasoning, which injects table reasoning skills through synthetic reasoning examples and is fine-tuned on the WikiTableQuestions dataset

Natural Language ProcessingTransformersEnglish

PISCES is a pretrained multilingual summarization model that acquires language modeling, cross-lingual capability, and summarization skills through a three-stage pretraining process.

Natural Language ProcessingTransformers

SkillSpan is a model designed for extracting hard and soft skills from English job postings, based on the BERT architecture with domain adaptation optimizations.

Natural Language ProcessingTransformers

SkillSpan is a model for extracting hard and soft skills from English job postings, optimized based on the BERT architecture, suitable for analyzing labor market dynamics.

Natural Language ProcessingTransformers

JobBERT is a recruitment domain pre-trained model based on BERT, specifically designed for extracting hard skills and soft skills from job postings.

Natural Language ProcessingTransformersEnglish

This model is a high-performance open-domain chatbot capable of integrating multiple dialogue skills such as questioning, answering, knowledge demonstration, and empathy.

Natural Language ProcessingTransformersEnglish

BlenderBot is an open-domain chatbot model focused on multi-turn dialogue and the integration of various conversational skills.

Natural Language ProcessingTransformersEnglish