models(gallery): add llama3.1-8b-enigma (#4146)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-11-14 11:04:36 +01:00 committed by GitHub
parent 8a89aafc8c
commit 8ab7517294
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -2653,6 +2653,25 @@
- filename: Tess-3-Llama-3.1-70B.Q4_K_M.gguf
sha256: 81625defcbea414282f490dd960b14afdecd7734e0d77d8db2da2bf5c21261aa
uri: huggingface://mradermacher/Tess-3-Llama-3.1-70B-GGUF/Tess-3-Llama-3.1-70B.Q4_K_M.gguf
- !!merge <<: *llama31
name: "llama3.1-8b-enigma"
icon: https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/it7MY5MyLCLpFQev5dUis.jpeg
urls:
- https://huggingface.co/ValiantLabs/Llama3.1-8B-Enigma
- https://huggingface.co/mradermacher/Llama3.1-8B-Enigma-GGUF
description: |
Enigma is a code-instruct model built on Llama 3.1 8b.
High quality code instruct performance within the Llama 3 Instruct chat format
Finetuned on synthetic code-instruct data generated with Llama 3.1 405b. Find the current version of the dataset here!
Overall chat performance supplemented with generalist synthetic data.
This is the 2024-10-02 release of Enigma for Llama 3.1 8b, enhancing code-instruct and general chat capabilities.
overrides:
parameters:
model: Llama3.1-8B-Enigma.Q4_K_M.gguf
files:
- filename: Llama3.1-8B-Enigma.Q4_K_M.gguf
sha256: e98c9909ee3b74b11d50d4c4f17178502e42cd936215ede0c64a7b217ae665bb
uri: huggingface://mradermacher/Llama3.1-8B-Enigma-GGUF/Llama3.1-8B-Enigma.Q4_K_M.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"