Releasesby GlyphTransformers 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.
Also shipped Oct 26, 2026Hugging Face in October 2026 →
Conversation logging for Conversational analytics in BigQuery is generally available
BigQuery now supports logging data agent conversations directly to a BigQuery table within the agent's project.
Improved Lakeflow Performance Observability will soon be available by default for workspaces with the compliance security profile enabled
Databricks is enabling improved Lakeflow performance observability by default for workspaces with the compliance security profile.
Looker (Google Cloud core) data lineage is generally available
Data lineage for Looker (Google Cloud core) is now generally available, providing end-to-end visibility for LookML dashboards and Conversational Analytics agents.
BigQuery Python user-defined functions support volume mounts in preview
Python user-defined functions in BigQuery now support volume mounts, allowing users to access dependency files directly from Cloud Storage.
QuickBooks connector is available in Beta
The managed QuickBooks connector is now available in beta, enabling incremental ingestion of accounting data into Databricks.
Looker-managed Model Context Protocol (MCP) server is generally available
The Looker-managed MCP server is now generally available, allowing AI agents to interact with business data and LookML models without middleware.
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 Patch release v5.22.1
Transformers patch release v5.22.1 fixes documentation errors.
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.