From 0d590a4044b4b4fec6046c54213eaeb8216147cf Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 20 May 2025 12:03:02 +0200 Subject: [PATCH] chore(model gallery): add smolvlm2-256m-video-instruct (#5417) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 077c12679..75046349f 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -106,6 +106,25 @@ - filename: mmproj-SmolVLM2-500M-Video-Instruct-f16.gguf sha256: b5dc8ebe7cbeab66a5369693960a52515d7824f13d4063ceca78431f2a6b59b0 uri: huggingface://ggml-org/SmolVLM2-500M-Video-Instruct-GGUF/mmproj-SmolVLM2-500M-Video-Instruct-f16.gguf +- !!merge <<: *smolvlm + name: "smolvlm2-256m-video-instruct" + icon: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM2_banner.png + urls: + - https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct + - https://huggingface.co/ggml-org/SmolVLM2-256M-Video-Instruct-GGUF + description: | + SmolVLM2-256M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.38GB of GPU RAM for video inference. This efficiency makes it particularly well-suited for on-device applications that require specific domain fine-tuning and computational resources may be limited. + overrides: + parameters: + model: SmolVLM2-256M-Video-Instruct-Q8_0.gguf + mmproj: mmproj-SmolVLM2-256M-Video-Instruct-Q8_0.gguf + files: + - filename: SmolVLM2-256M-Video-Instruct-Q8_0.gguf + sha256: af7ce9951a2f46c4f6e5def253e5b896ca5e417010e7a9949fdc9e5175c27767 + uri: huggingface://ggml-org/SmolVLM2-256M-Video-Instruct-GGUF/SmolVLM2-256M-Video-Instruct-Q8_0.gguf + - filename: mmproj-SmolVLM2-256M-Video-Instruct-Q8_0.gguf + sha256: d34913a588464ff7215f086193e0426a4f045eaba74456ee5e2667d8ed6798b1 + uri: huggingface://ggml-org/SmolVLM2-256M-Video-Instruct-GGUF/mmproj-SmolVLM2-256M-Video-Instruct-Q8_0.gguf - &qwen3 url: "github:mudler/LocalAI/gallery/qwen3.yaml@master" name: "qwen3-30b-a3b"