Ollama has released version v0.40.0-rc1, which includes updates to its mlx integration. These changes focus on aligning tokenizer semantics with publisher standards, ensuring consistent handling of pretokenization, Unicode boundaries, and token normalization. The release also adds shared Go and Python reference cases for published tokenizers and addresses configuration precedence and byte fallback behaviors. AI
IMPACT Improves the underlying tokenization process for models run through Ollama's mlx integration.
RANK_REASON This is a release of a software tool, not a frontier model or significant industry event.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →