models(gallery): add suzume-llama-3-8B-multilingual-gguf (#2194)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-04-30 23:24:28 +02:00 committed by GitHub
parent cd31f8d865
commit b24d44dc56
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -399,6 +399,22 @@
- filename: Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf
sha256: 265ded6a4f439bec160f394e3083a4a20e32ebb9d1d2d85196aaab23dab87fb2
uri: huggingface://Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix/Aura_Uncensored_l3_8B-Q4_K_M-imat.gguf
- <<: *llama3
name: "suzume-llama-3-8B-multilingual"
urls:
- https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-gguf
icon: https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/kg3QjQOde0X743csGJT-f.png
description: |
This Suzume 8B, a multilingual finetune of Llama 3.
Llama 3 has exhibited excellent performance on many English language benchmarks. However, it also seemingly been finetuned on mostly English data, meaning that it will respond in English, even if prompted in other languages.
overrides:
parameters:
model: suzume-llama-3-8B-multilingual-Q4_K_M.gguf
files:
- filename: suzume-llama-3-8B-multilingual-Q4_K_M.gguf
sha256: be197a660e56e51a24a0e0fecd42047d1b24e1423afaafa14769541b331e3269
uri: huggingface://lightblue/suzume-llama-3-8B-multilingual-gguf/ggml-model-Q4_K_M.gguf
- &dolphin
name: "dolphin-2.9-llama3-8b"
url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master"