chore(model): add l3.1-ms-astoria-70b-v2 to the gallery (#4159)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-11-15 14:48:29 +01:00 committed by GitHub
parent c53c0b068b
commit f69afb457c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -2772,6 +2772,28 @@
- filename: L3.1-8B-Slush.i1-Q4_K_M.gguf
sha256: 98c53cd1ec0e2b00400c5968cd076a589d0c889bca13ec52abfe4456cfa039be
uri: huggingface://mradermacher/L3.1-8B-Slush-i1-GGUF/L3.1-8B-Slush.i1-Q4_K_M.gguf
- !!merge <<: *llama31
icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/C-ndfxAGdf21DjchZcf2p.png
name: "l3.1-ms-astoria-70b-v2"
urls:
- https://huggingface.co/Steelskull/L3.1-MS-Astoria-70b-v2
- https://huggingface.co/bartowski/L3.1-MS-Astoria-70b-v2-GGUF
description: |
This model is a remake of the original astoria with modern models and context sizes its goal is to merge the robust storytelling of mutiple models while attempting to maintain intelligence.
Use Llama 3 Format or meth format (llama 3 refuses to work with stepped thinking but meth works)
- model: migtissera/Tess-3-Llama-3.1-70B
- model: NeverSleep/Lumimaid-v0.2-70B
- model: Sao10K/L3.1-70B-Euryale-v2.2
- model: ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.2
- model: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
overrides:
parameters:
model: L3.1-MS-Astoria-70b-v2-Q4_K_M.gguf
files:
- filename: L3.1-MS-Astoria-70b-v2-Q4_K_M.gguf
sha256: c02658ead1ecdc25c7218b8d9d11786f19c16d64f0d453082998e313edb0d4a6
uri: huggingface://bartowski/L3.1-MS-Astoria-70b-v2-GGUF/L3.1-MS-Astoria-70b-v2-Q4_K_M.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"