IBM has released Granite Embedding Multilingual R2, an open-source embedding model under the Apache 2.0 license. This model supports a 32K context window and aims to achieve top-tier search quality with fewer than 100 million parameters. The release also includes a guide to profiling in PyTorch, focusing on the torch.profiler tool. AI
IMPACT Provides a new open-source embedding model for multilingual tasks and offers a guide for PyTorch performance optimization.
RANK_REASON Release of an open-source model and accompanying technical guide.
Read on Mastodon — fosstodon.org →
- 32K Context
- Apache Software License 2.0
- Granite Embedding Multilingual R2
- Hugging Face
- IBM
- PyTorch
- torch.profiler
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →