AutoModelForImageTextToText

This preview release introduces support for the InternVL 2.5 and 3 family of multimodal models, featuring a native multimodal pre-training paradigm and state-of-the-art performance on visual-linguistic tasks.

This release introduces Mistral 3 (Mistral Small 3.1) to the Transformers library, a 24B parameter model featuring 128k context length and advanced vision-language capabilities.

This release introduces Aya Vision 8B and 32B, multilingual multimodal models combining SigLIP-2 vision encoders with Cohere language models, available via a specialized transformers release tag.

This release introduces SmolVLM-2, a lightweight vision-language model based on Idefics3 and SmolLM2 that supports multi-image and video processing.

v0.8.1 is a maintenance release focusing on V1 engine stability, adding Zamba2 support, and enabling LoRA for embedding models. It includes critical fixes for sampling dtypes, quantization, and TPU performance.