mirror of
https://github.com/mudler/LocalAI.git
synced 2024-12-18 20:27:57 +00:00
models(gallery): add darkens-8b (#3863)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
0da16c73ba
commit
52bc463a3f
@ -2425,6 +2425,21 @@
|
||||
- filename: Tor-8B.Q4_K_M.gguf
|
||||
sha256: 9dd64bd886aa7682b6179340449b38feda405b44722ef7ac752cedb807af370e
|
||||
uri: huggingface://QuantFactory/Tor-8B-GGUF/Tor-8B.Q4_K_M.gguf
|
||||
- !!merge <<: *mistral03
|
||||
name: "darkens-8b"
|
||||
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/Delta-Vector/Darkens-8B
|
||||
- https://huggingface.co/QuantFactory/Darkens-8B-GGUF
|
||||
description: |
|
||||
This is the fully cooked, 4 epoch version of Tor-8B, this is an experimental version, despite being trained for 4 epochs, the model feels fresh and new and is not overfit, This model aims to have generally good prose and writing while not falling into claude-isms, it follows the actions "dialogue" format heavily.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Darkens-8B.Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Darkens-8B.Q4_K_M.gguf
|
||||
sha256: f56a483e10fd00957460adfc16ee462cecac892a4fb44dc59e466e68a360fd42
|
||||
uri: huggingface://QuantFactory/Darkens-8B-GGUF/Darkens-8B.Q4_K_M.gguf
|
||||
- &mudler
|
||||
### START mudler's LocalAI specific-models
|
||||
url: "github:mudler/LocalAI/gallery/mudler.yaml@master"
|
||||
|
Loading…
Reference in New Issue
Block a user