alikia2x/sparkastML
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 3 Wiki Activity

3 Releases 3 Tags

RSS Feed
  • v2-model 580753bb6f
    Compare

    model: v2 | Chinese-English NMT v1.1 Stable

    alikia2x released this 2024-09-17 12:21:02 +00:00 | 14 commits to main since this release

    sparkastML's first translation model is now available!

    Details

    • Source Language: Chinese (Simplified)
    • Target Language: English
    • Training Time: 5 hours, 20,000 steps
    • Training Device: RTX 3080 (20GB)
    • Corpus Size: Over 10 million sentences
    • Validation BLEU Score: 17

    Model & Checkpoint Download

    You can directly download the final Argos translate model below. If you want to fine-tune the model or do anything you want, we also offers the checkpoint.

    Downloads
  • v1-model f28f83b48e
    Compare

    model: v1 | Intention Classification Stable

    alikia2x released this 2024-09-16 09:36:31 +00:00 | 32 commits to main since this release

    This release includes the most recent version of the trained model for the intention classification component.

    Downloads
  • v1-dataset 3ebeaf4655
    Compare

    dataset: v1 Stable

    alikia2x released this 2024-09-16 09:36:20 +00:00 | 17 commits to main since this release

    sparkastML Datasets

    This repository contains datasets published by the sparkastML project.

    Translation ZH-EN

    This dataset features high-quality, fresh synthetic data comprising over 100,000 sentences of Chinese-English parallel corpora.

    Details

    • Source Language: Chinese (Simplified)
    • Target Language: English
    • Version: 1
    • Last Update: 2024/09/16
    • LICENSE: CC-BY 4.0
    Downloads