chore(model gallery): add ilsp_llama-krikri-8b-instruct (#4795)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-02-10 09:54:54 +01:00 committed by GitHub
parent 8cd51570e5
commit c330360785
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -5600,6 +5600,21 @@
- filename: Selene-1-Mini-Llama-3.1-8B-Q4_K_M.gguf
sha256: 908e6ce19f7cd3d7394bd7c38e43de2f228aca6aceda35c7ee70d069ad60493e
uri: huggingface://bartowski/Selene-1-Mini-Llama-3.1-8B-GGUF/Selene-1-Mini-Llama-3.1-8B-Q4_K_M.gguf
- !!merge <<: *llama31
name: "ilsp_llama-krikri-8b-instruct"
icon: https://huggingface.co/ilsp/Llama-Krikri-8B-Instruct/resolve/main/llama-krikri-image.jpg
urls:
- https://huggingface.co/ilsp/Llama-Krikri-8B-Instruct
- https://huggingface.co/bartowski/ilsp_Llama-Krikri-8B-Instruct-GGUF
description: |
Following the release of Meltemi-7B on the 26th March 2024, we are happy to welcome Krikri to the family of ILSP open Greek LLMs. Krikri is built on top of Llama-3.1-8B, extending its capabilities for Greek through continual pretraining on a large corpus of high-quality and locally relevant Greek texts. We present Llama-Krikri-8B-Instruct, along with the base model, Llama-Krikri-8B-Base.
overrides:
parameters:
model: ilsp_Llama-Krikri-8B-Instruct-Q4_K_M.gguf
files:
- filename: ilsp_Llama-Krikri-8B-Instruct-Q4_K_M.gguf
sha256: 0ae3a259f03ed79ba634a99ee3bfc672d785b5594b2f71053ed8cb760098abb6
uri: huggingface://bartowski/ilsp_Llama-Krikri-8B-Instruct-GGUF/ilsp_Llama-Krikri-8B-Instruct-Q4_K_M.gguf
- &deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" ## Deepseek
name: "deepseek-coder-v2-lite-instruct"