NuExtract: A LLM for Structured Extraction
NuExtract is a structure extraction model by NuMind, offering tiny and large versions. NuMind also provides NuNER Zero and sentiment analysis models. Mistral 7B, by Mistral AI, excels in benchmarks with innovative attention mechanisms.
Read original article
NuExtract is a structure extraction model developed by NuMind, based on the phi-3-mini architecture and fine-tuned on a private synthetic dataset for information extraction. Users can input text and a JSON template specifying the information to extract, with output reflecting the original text. NuExtract offers tiny and large versions for different needs. Additionally, NuMind provides other models like NuNER Zero for zero-shot NER and sentiment analysis models. The model can be accessed through Hugging Face's platform. In a related development, Mistral 7B, a language model by Mistral AI, outperforms other models in various benchmarks and tasks, leveraging innovative attention mechanisms for improved performance. Mistral AI's models are available under the Apache 2.0 license. The code and webpage for Mistral 7B are accessible for further exploration.
Related
Open Source Python ETL
Amphi is an open-source Python ETL tool for data extraction, preparation, and cleaning. It offers a graphical interface, supports structured and unstructured data, promotes low-code development, and integrates generative AI. Available for public beta testing in JupyterLab.
HybridNeRF: Efficient Neural Rendering
HybridNeRF combines surface and volumetric representations for efficient neural rendering, achieving 15-30% error rate improvement over baselines. It enables real-time framerates of 36 FPS at 2K×2K resolutions, outperforming VR-NeRF in quality and speed on various datasets.
AI discovers new rare-earth-free magnet at 200 times the speed of man
Materials Nexus and the University of Sheffield collaborated to create MagNex, a rare-earth-free permanent magnet using AI, significantly faster than traditional methods. MagNex offers a sustainable, cost-effective alternative for powerful magnets.
JEPA (Joint Embedding Predictive Architecture)
Yann LeCun's Joint Embedding Predictive Architecture (JEPA) enhances AI by emphasizing world models, self-supervised learning, and abstract representations. JEPA predicts future states by transforming inputs into abstract representations, handling uncertainty, and enabling complex predictions through multistep or hierarchical structures. Several models like I-JEPA, MC-JEPA, and V-JEPA have been developed to process visual data and improve AI's understanding of images and videos, moving towards human-like interaction with the world.
Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs
The study presents a method to boost Large Language Models' retrieval and reasoning abilities for long-context inputs by fine-tuning on a synthetic dataset. Results show significant improvements in information retrieval and reasoning skills.
3 comments* Out-of-the-box fine-tuned model for extraction makes for an easier start, so happy to see this out there
* ... But presumably one of the next steps in a project using it is doing further fine-tuning on their data after some use, but this is a closed model with closed data, so preserving the original fine tuning quality is unclear without that
Related
Open Source Python ETL
Amphi is an open-source Python ETL tool for data extraction, preparation, and cleaning. It offers a graphical interface, supports structured and unstructured data, promotes low-code development, and integrates generative AI. Available for public beta testing in JupyterLab.
HybridNeRF: Efficient Neural Rendering
HybridNeRF combines surface and volumetric representations for efficient neural rendering, achieving 15-30% error rate improvement over baselines. It enables real-time framerates of 36 FPS at 2K×2K resolutions, outperforming VR-NeRF in quality and speed on various datasets.
AI discovers new rare-earth-free magnet at 200 times the speed of man
Materials Nexus and the University of Sheffield collaborated to create MagNex, a rare-earth-free permanent magnet using AI, significantly faster than traditional methods. MagNex offers a sustainable, cost-effective alternative for powerful magnets.
JEPA (Joint Embedding Predictive Architecture)
Yann LeCun's Joint Embedding Predictive Architecture (JEPA) enhances AI by emphasizing world models, self-supervised learning, and abstract representations. JEPA predicts future states by transforming inputs into abstract representations, handling uncertainty, and enabling complex predictions through multistep or hierarchical structures. Several models like I-JEPA, MC-JEPA, and V-JEPA have been developed to process visual data and improve AI's understanding of images and videos, moving towards human-like interaction with the world.
Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs
The study presents a method to boost Large Language Models' retrieval and reasoning abilities for long-context inputs by fine-tuning on a synthetic dataset. Results show significant improvements in information retrieval and reasoning skills.