Releasesby GlyphTransformers Patch release v5.22.2
This patch release includes security hardening for Jinja sandboxing and fixes for distributed training using NCCL.
Also shipped Nov 6, 2026Hugging Face in November 2026 →
Gemini Enterprise: End of Gemini Code Assist entitlement for existing subscriptions
Bundled Gemini Code Assist entitlements for existing Gemini Enterprise subscriptions will be removed on March 31, 2027. New subscriptions no longer include this entitlement as of October 9, 2026, with users directed to Google Antigravity for coding assistance.
Gemini Enterprise: Video generation upgrades to Omni 1.2 Flash
Gemini Omni 1.2 Flash is now generally available for video generation, replacing Veo 3.1. The update improves video clarity and instruction following.
Gemini Enterprise: Adobe data store (Preview)
The Adobe data store is now available in public preview for Gemini Enterprise. Users can search, share, and manage Adobe Creative Cloud assets and edit images using natural language.
BigQuery Graph and GQL queries are available with on-demand pricing
BigQuery Graph and Graph Query Language (GQL) are now supported for users on on-demand pricing models.
BigQuery Data Transfer Service for Shopify deprecates specific fields
Effective January 31, 2027, the BigQuery Data Transfer Service for Shopify will no longer support the legacyMode field in DeliveryProfile and the permitSkuSharing field in FulfillmentService.
BigQuery adds organization policy controls for models in preview
Users can now define custom organization policies to allow or deny specific operations on models within BigQuery. This feature is currently in preview.
More from TransformersEvery Transformers release →
Transformers Patch release v5.22.1
Transformers patch release v5.22.1 fixes documentation errors.
Transformers 5.22.0: Mistral Large 4 (Le Chonk)
Transformers v5.22.0 adds support for Mistral Large 4, a 1-trillion parameter multimodal Mixture-of-Experts model featuring a 1-million token context window.
Transformers Patch release v5.21.1
Transformers patch release v5.21.1 fixes the rope_scaling setter for model configs to resolve remote code loading errors in vLLM.
Transformers Release: v5.21.0
Transformers v5.21.0 introduces the MiniCPM-OCR document-understanding model and the Flint mixture-of-experts language model. These additions expand the library's support for specialized vision and language tasks.
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.