About 17,100 results
Open links in new tab
  1. Nomic Embed: Training a Reproducible Long Context Text Embedder

    Feb 26, 2025 · We release the training code and model weights under an Apache 2.0 license. In contrast with other open-source models, we release the full curated training data and code that …

  2. Improving Multilingual Capabilities with Cultural and Local...

    Feb 16, 2025 · Our results indicate that modest fine-tuning with culturally and locally informed data can bridge performance gaps without incurring significant computational overhead. We release our …

  3. Signatory: differentiable computations of the signature and...

    Jan 12, 2021 · The license is Apache-2.0. One-sentence Summary: Differentiable, GPU-capable implementations of the (log)signature transform via novel algorithms. Code Of Ethics: I acknowledge …

  4. Extensive eval-uations demonstrate that TOTO achieves state-of-the-art performance on on established gen-eral purpose time series forecasting benchmarks. TOTO’s model weights, inference code, and …

  5. In Section 5 we present our implementations for (1) converting RML to SPARQL (2) the NORSE SPARQL extensions for Apache Jena’s ARQ query engine and (3) the implementation of a SPARQL …

  6. Kemafor Anyanwu - OpenReview

    Scalable Exploratory Search on Knowledge Graphs Using Apache Spark Avimanyu Mukhopadhyay, HyeongSik Kim, Kemafor Anyanwu Published: 31 Dec 2017, Last Modified: 14 Oct 2023 WETICE 2018

  7. LLM-Datasets is publicly available as a Python package and its source code is on GitHub with an Apache-2.0 license.1

  8. able under the apache license, version arXiv preprint arXiv:2211.06934, 2022. Chandan Singh, William Murdoch, and Bin Yu. Interpretations are useful: penaliz-ing explanations t align neural networks with …

  9. Users are generally free to do as they wish with the source code, as long as they include a copy of the license and attribution to the original authors in the copies or derivative works. Examples of …

  10. Beyond our Hacker Cup dataset, participants can use any open data, for example, the competition dataset aggregated by DeepMind and released under Apache-2 license. We encourage competitors …