Search

7 results for "multimodal"

Products and releases 7

Transformers Release v5.19.0Hugging Face, Oct 6, 2026: Release v5.19.0 New Model additions EmbeddingGemma2 EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.
Transformers Release v5.20.0Hugging Face, Oct 15, 2026: 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.
Transformers Patch release v5.20.2Hugging Face, Oct 19, 2026: 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.
Transformers 5.22.0: Mistral Large 4 (Le Chonk)Hugging Face, Oct 29, 2026: 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.
Le Chonk: Built for Coders, Trusted by DefendersMistral AI, Oct 29, 2026: Mistral AI released the open weights for Le Chonk, a 1T parameter multimodal model.
Embed 5 and Rerank 5 Are Now Available on OpenRouterCohere, Nov 4, 2026: Cohere made Embed 5 (Pro and Fast) and Rerank 5 (Pro and Fast) models available on OpenRouter, supporting multimodal inputs and unified embedding spaces.
Kimi K3.1 Pro now has more ZDR providers on AI GatewayVercel, Nov 4, 2026: Vercel AI Gateway expanded Zero Data Retention provider support for Moonshot AI Kimi K3.1 Pro and K3.1 Pro Highspeed models, supporting 1M token contexts and multimodal input.