dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-25 12:15:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 18

chore(model gallery): add smolvlm-instruct

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-05-20 11:32:36 +02:00
parent 1db51044bb
commit 5fc4a9161a
1 changed files with 19 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

19
gallery/index.yaml
View file

@ -47,6 +47,25 @@
- filename: SmolVLM-500M-Instruct-Q8_0.gguf - filename: SmolVLM-500M-Instruct-Q8_0.gguf
sha256: 9d4612de6a42214499e301494a3ecc2be0abdd9de44e663bda63f1152fad1bf4 sha256: 9d4612de6a42214499e301494a3ecc2be0abdd9de44e663bda63f1152fad1bf4
uri: huggingface://ggml-org/SmolVLM-500M-Instruct-GGUF/SmolVLM-500M-Instruct-Q8_0.gguf uri: huggingface://ggml-org/SmolVLM-500M-Instruct-GGUF/SmolVLM-500M-Instruct-Q8_0.gguf
- !!merge <<: *smolvlm
name: "smolvlm-instruct"
icon: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM.png
urls:
- https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct
- https://huggingface.co/ggml-org/SmolVLM-Instruct-GGUF
description: |
SmolVLM is a compact open multimodal model that accepts arbitrary sequences of image and text inputs to produce text outputs. Designed for efficiency, SmolVLM can answer questions about images, describe visual content, create stories grounded on multiple images, or function as a pure language model without visual inputs. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks.
overrides:
parameters:
model: SmolVLM-Instruct-Q4_K_M.gguf
mmproj: mmproj-SmolVLM-Instruct-Q8_0.gguf
files:
- filename: SmolVLM-Instruct-Q4_K_M.gguf
sha256: dc80966bd84789de64115f07888939c03abb1714d431c477dfb405517a554af5
uri: https://huggingface.co/ggml-org/SmolVLM-Instruct-GGUF/resolve/main/SmolVLM-Instruct-Q4_K_M.gguf
- filename: mmproj-SmolVLM-Instruct-Q8_0.gguf
sha256: 86b84aa7babf1ab51a6366d973b9d380354e92c105afaa4f172cc76d044da739
uri: https://huggingface.co/ggml-org/SmolVLM-Instruct-GGUF/resolve/main/mmproj-SmolVLM-Instruct-Q8_0.gguf
- &qwen3 - &qwen3
url: "github:mudler/LocalAI/gallery/qwen3.yaml@master" url: "github:mudler/LocalAI/gallery/qwen3.yaml@master"
name: "qwen3-30b-a3b" name: "qwen3-30b-a3b"