ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-01-27 14:49:39 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

chore(model gallery): add control-nanuq-8b (#4506)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-12-28 10:49:53 +01:00 committed by GitHub
parent afd0af987d
commit 9b0983d027
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
gallery/index.yaml
View File

@ -4302,6 +4302,21 @@
- filename: Llama-3.1-8B-Open-SFT-Q4_K_M.gguf
sha256: ce75152763c48c5386fe59652cc921aae456da36ab82af3d9e2080f603f45132
uri: huggingface://bartowski/Llama-3.1-8B-Open-SFT-GGUF/Llama-3.1-8B-Open-SFT-Q4_K_M.gguf
- !!merge <<: *llama31
name: "control-nanuq-8b"
icon: https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/6L-SXxQZ2nxYwvIjnlzN8.png
urls:
- https://huggingface.co/Delta-Vector/Control-Nanuq-8B
- https://huggingface.co/QuantFactory/Control-Nanuq-8B-GGUF
description: |
The model is a fine-tuned version of LLaMA 3.1 8B Supernova, designed to be "short and sweet" by minimizing narration and lengthy responses. It was fine-tuned over 4 epochs using OpenCAI and RP logs, with DPO applied to enhance coherence. Finally, KTO reinforcement learning was implemented on version 1.1, significantly improving the model's prose and creativity.
overrides:
parameters:
model: Control-Nanuq-8B.Q4_K_M.gguf
files:
- filename: Control-Nanuq-8B.Q4_K_M.gguf
sha256: 5aa3b929cbcaf62709fef58d6f630c2df1185d774d0074c7e750cb03c53b744e
uri: huggingface://QuantFactory/Control-Nanuq-8B-GGUF/Control-Nanuq-8B.Q4_K_M.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"