Releasesby GlyphTransformers Patch release v5.22.1
Transformers patch release v5.22.1 fixes documentation errors.
Also shipped Oct 30, 2026Hugging Face in October 2026 →
Microsoft Graph Logs connector is available in Beta
The Microsoft Graph Logs connector is now in beta for Databricks Lakeflow Connect, supporting incremental ingestion of security alerts from Microsoft security products.
Hybrid table support for Google Cloud (Preview)
Snowflake hybrid tables are now supported in all Google Cloud commercial regions in preview.
External OAuth for Snowflake Postgres (General availability)
External OAuth for Snowflake Postgres is now generally available, allowing authentication via external identity providers.
Spanner supports equality and ordering comparisons on JSONB and JSON values
Spanner now allows equality and ordering comparisons on JSONB and JSON values directly in GROUP_BY and ORDER BY clauses. It also supports implicit type coercion and search indexes for JSON equality operations.
[In preview] Public Preview: Support database-level managed identity (including FIC) in Create Database Scoped Credential T-SQL
Users can now assign a user-assigned managed identity to individual databases in Azure SQL Database. This enables secure access to files in Azure Blob Storage and Data Lake Storage Gen2 via external tables and OPENROWSET.
Inference request metadata logging (GA)
Inference request metadata logging is now generally available for Gemini and Claude models. It records model usage, latency, and error codes without capturing prompt or response content.
More from TransformersEvery Transformers release →
Transformers 5.22.0: Mistral Large 4 (Le Chonk)
New Models Mistral Large 4 (Le Chonk) Mistral Large 4 is Mistral's largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's own datacenters...
Transformers Patch release v5.21.1
Patch release v5.21.1 ** Fix rope_scaling setter for configs that assign it during init (#50080 ) We broke remote code loading in vllm, this fixes it sorry everyone!
Transformers Release: v5.21.0
Release v5.21.0 New Model additions MiniCPM-OCR MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language model.
ThinkingBox-Training released
ThinkingBox-Training is now available to post-train agents using executable database state as a reward. The framework uses offline policy-relative difficulty to select training tasks and improve agent dependability.
Transformers Patch release v5.20.2
Patch release: v5.20.2 This patch notably solves an issue where some inputs could loose their original type inside prepare_inputs_for_generation in generate, leading to problems with multimodal models. It also fixes some other issues listed on the below commits.
Transformers Release v5.20.1
Release v5.20.1 Special surprise including the new model Beam from Reflection AI :partying_face: Beam is a token-efficient, frontier-scale model focused on coding and agentic use cases. It is built for teams that want to run a powerful model on their own hardware, infrastructure, or cloud, and customize it to their specific needs.
Transformers Release v5.20.0
Release v5.20.0 New Model additions Muse Spark Open Muse Spark Open is a multimodal mixture-of-experts model from Meta that takes text, images, audio, and video as input and generates text. It has 816B total parameters (42B active per token) and a context window of up to 1,048,576 tokens shared across modalities.
Transformers Release v5.19.0
Release v5.19.0 New Model additions EmbeddingGemma2 EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture. It encodes text, images, audio, and video, individually or combined in one input, into a shared 768-dimensional vector space for cross-modal retrieval, semantic similarity, clustering, and classification.