MR_midtrain_9B_v3 is a 9-billion parameter multimodal model hosted on Hugging Face. It supports vision and text inputs using a custom chat template with vision tokens. The model is designed for researchers and developers who want to experiment with or fine-tune a mid-sized open-weight multimodal foundation model. It can be used via the Transformers library or Hugging Face Inference Endpoints.
In the Foundation models & chat space, MR Midtrain 9B takes a focused approach. It focuses on accessing and running a pre-trained 9B-parameter multimodal model without training from scratch. It is built as an open-source project for AI researchers and developers. The project is open source (Open Source). It ships for the web and API.
Behind MR Midtrain 9B is HerrHruby, and it first shipped in 2024. Key capabilities include Multimodal Input, Vision Processing, and Chat Template. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match