Showing 2 open source projects for "decoder"

View related business solutions
  • Go from Data Warehouse to Data and AI platform with BigQuery Icon
    Go from Data Warehouse to Data and AI platform with BigQuery

    Build, train, and run ML models with simple SQL. Automate data prep, analysis, and predictions with built-in AI assistance from Gemini.

    BigQuery is more than a data warehouse—it's an autonomous data-to-AI platform. Use familiar SQL to train ML models, run time-series forecasts, and generate AI-powered insights with native Gemini integration. Built-in agents handle data engineering and data science workflows automatically. Get $300 in free credit, query 1 TB, and store 10 GB free monthly.
    Try BigQuery Free
  • 99.99% Uptime for MySQL and PostgreSQL on Google Cloud Icon
    99.99% Uptime for MySQL and PostgreSQL on Google Cloud

    Enterprise Plus edition delivers sub-second maintenance downtime and 2x read/write performance. Built for critical apps.

    Cloud SQL Enterprise Plus gives you a 99.99% availability SLA with near-zero downtime maintenance—typically under 10 seconds. Get 2x better read/write performance, intelligent data caching, and 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server with built-in vector search for gen AI apps. New customers get $300 in free credit.
    Try Cloud SQL Free
  • 1
    Basaran

    Basaran

    Basaran, an open-source alternative to the OpenAI text completion API

    ...The open source community will eventually witness the Stable Diffusion moment for large language models (LLMs), and Basaran allows you to replace OpenAI's service with the latest open-source model to power your application without modifying a single line of code. Stream generation using various decoding strategies. Support both decoder-only and encoder-decoder models. Detokenizer that handles surrogates and whitespace. Multi-GPU support with optional 8-bit quantization. Real-time partial progress using server-sent events. Compatible with OpenAI API and client libraries. Comes with a fancy web-based playground. Docker images are available on Docker Hub and GitHub Packages.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 2
    CPT

    CPT

    CPT: A Pre-Trained Unbalanced Transformer

    A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation. We replace the old BERT vocabulary with a larger one of size 51271 built from the training data, in which we 1) add missing 6800+ Chinese characters (most of them are traditional Chinese characters); 2) remove redundant tokens (e.g. Chinese character tokens with ## prefix); 3) add some English tokens to reduce OOV. Position Embeddings We extend the max_position_embeddings from 512 to 1024. We...
    Downloads: 0 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • Next
MongoDB Logo MongoDB