models(gallery): add shieldgemma (#3105)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-08-01 09:58:28 +02:00 committed by GitHub
parent d590532d7f
commit e4b91e9dbb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1331,6 +1331,20 @@
- filename: tarnished-9b.i1-Q4_K_M.gguf - filename: tarnished-9b.i1-Q4_K_M.gguf
sha256: 62ab09124b3f6698bd94ef966533ae5d427d87f6bdc09f6f46917def96420a0c sha256: 62ab09124b3f6698bd94ef966533ae5d427d87f6bdc09f6f46917def96420a0c
uri: huggingface://mradermacher/tarnished-9b-i1-GGUF/tarnished-9b.i1-Q4_K_M.gguf uri: huggingface://mradermacher/tarnished-9b-i1-GGUF/tarnished-9b.i1-Q4_K_M.gguf
- !!merge <<: *gemma
name: "shieldgemma-9b-i1"
urls:
- https://huggingface.co/google/shieldgemma-9b
- https://huggingface.co/mradermacher/shieldgemma-9b-i1-GGUF
description: |
ShieldGemma is a series of safety content moderation models built upon Gemma 2 that target four harm categories (sexually explicit, dangerous content, hate, and harassment). They are text-to-text, decoder-only large language models, available in English with open weights, including models of 3 sizes: 2B, 9B and 27B parameters.
overrides:
parameters:
model: shieldgemma-9b.i1-Q4_K_M.gguf
files:
- filename: shieldgemma-9b.i1-Q4_K_M.gguf
sha256: ffa7eaadcc0c7d0544fda5b0d86bba3ffa3431b673e5b2135f421cfe65bd8732
uri: huggingface://mradermacher/shieldgemma-9b-i1-GGUF/shieldgemma-9b.i1-Q4_K_M.gguf
- &llama3 - &llama3
url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master" url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master"
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png