From 1db51044bbeb336aa6d7dc2c159c99352e9e8744 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 20 May 2025 11:25:32 +0200 Subject: [PATCH] chore(model gallery): add smolvlm-500m-instruct (#5413) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 5553d790..7b4299a1 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -29,6 +29,24 @@ - filename: SmolVLM-256M-Instruct-Q8_0.gguf sha256: 2a31195d3769c0b0fd0a4906201666108834848db768af11de1d2cef7cd35e65 uri: huggingface://ggml-org/SmolVLM-256M-Instruct-GGUF/SmolVLM-256M-Instruct-Q8_0.gguf +- !!merge <<: *smolvlm + name: "smolvlm-500m-instruct" + urls: + - https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct + - https://huggingface.co/ggml-org/SmolVLM-500M-Instruct-GGUF + description: | + SmolVLM-500M is a tiny multimodal model, member of the SmolVLM family. It accepts arbitrary sequences of image and text inputs to produce text outputs. It's designed for efficiency. SmolVLM can answer questions about images, describe visual content, or transcribe text. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on one image with 1.23GB of GPU RAM. + overrides: + parameters: + model: SmolVLM-500M-Instruct-Q8_0.gguf + mmproj: mmproj-SmolVLM-500M-Instruct-Q8_0.gguf + files: + - filename: mmproj-SmolVLM-500M-Instruct-Q8_0.gguf + sha256: d1eb8b6b23979205fdf63703ed10f788131a3f812c7b1f72e0119d5d81295150 + uri: huggingface://ggml-org/SmolVLM-500M-Instruct-GGUF/mmproj-SmolVLM-500M-Instruct-Q8_0.gguf + - filename: SmolVLM-500M-Instruct-Q8_0.gguf + sha256: 9d4612de6a42214499e301494a3ecc2be0abdd9de44e663bda63f1152fad1bf4 + uri: huggingface://ggml-org/SmolVLM-500M-Instruct-GGUF/SmolVLM-500M-Instruct-Q8_0.gguf - &qwen3 url: "github:mudler/LocalAI/gallery/qwen3.yaml@master" name: "qwen3-30b-a3b"