Releasesby IbisThinkingBox-Training released
GA3 days agoUnverifiedAdded Oct 25, 2026
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.
Topics: AI agents, Developer tools, Performance
More Transformers releases
Every Transformers releaseTransformers 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.
Transformers Release 5.18.0
New Model additions Nemotron 3 Diarization Nemotron 3 Diarization is an open-weight streaming speaker diarization model designed to determine "who spoke when" in real-world audio. It supports both streaming and offline inference, handles up to eight speakers, and orders speaker outputs by each speaker's first arrival in the input audio.
Transformers Release 5.17.0
Release v5.17.0 New Model additions HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared expert and routes every token to 8 of them. The context window is 1M tokens.
Transformers Release v5.16.1
Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) GLM-5.3-Flash GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series.
Transformers Release: v5.16.0
Release v5.16.0 New Model additions Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse Attention (QSA), and Per-Layer Embedding (PLE). GR is a Qwen-developed residual architecture that combines Hyper-Connection with GatedNorm.
Also shipped on Oct 22, 2026
Hugging Face in October 2026Trace and evaluate Cursor agents with Langfuse, powered by ClickHouse
Users can now connect Cursor to Langfuse to trace agent turns and analyze model and tool calls, with ClickHouse providing the underlying analytics infrastructure.
The AI.TRANSLATE function is generally available
The AI.TRANSLATE function is now generally available in BigQuery. It supports both standard Neural Machine Translation and Translation LLM capabilities for text string translation.
Replit Monitoring Agent: Your very own software engineering team
Replit Monitoring Agent is an autonomous tool that investigates production alerts, identifies causes, applies fixes, and deploys them to production for internal apps.
Microsoft Entra ID connector is available in Beta
The Microsoft Entra ID connector is now in beta for Databricks Lakeflow Connect. It supports incremental ingestion of users, groups, and audit logs using OAuth machine-to-machine authentication.
You can configure Direct VPC ingress for Cloud Run instances ( Preview )
Direct VPC ingress is now in preview for Cloud Run. This feature allows instances on a VPC network to use ephemeral private IP addresses for communication with other VPC resources.
Gemini Enterprise: Single-user quota limits
Gemini Enterprise administrators can now set single-user quota limits to prevent individual users from consuming the entire subscription quota pool. This feature is generally available.