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 claims to achieve top-tier search quality with less than 100 million parameters. Separately, a guide to using `torch.profiler` in PyTorch has been published, focusing on profiling techniques within the framework. AI
IMPACT Provides a new open-source embedding model for multilingual tasks and offers guidance on optimizing performance within PyTorch.
RANK_REASON The cluster contains an announcement of an open-source model release and a technical guide for a popular framework.
Read on Mastodon — sigmoid.social →
- 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 →