mirror of
https://github.com/mudler/LocalAI.git
synced 2024-12-24 06:46:39 +00:00
models(gallery): add control-8b-v1.1 (#4039)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
0b3a55b9fe
commit
d274df2fe2
@ -2033,6 +2033,20 @@
|
||||
- filename: Llama3.1-BestMix-Chem-Einstein-8B.Q4_K_M.gguf
|
||||
sha256: 1a53aa7124c731f33b0b616d7c66a6f78c6a133240acd9e3227f1188f743c1ee
|
||||
uri: huggingface://QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF/Llama3.1-BestMix-Chem-Einstein-8B.Q4_K_M.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "control-8b-v1.1"
|
||||
urls:
|
||||
- https://huggingface.co/Delta-Vector/Control-8B-V1.1
|
||||
- https://huggingface.co/QuantFactory/Control-8B-V1.1-GGUF
|
||||
description: |
|
||||
An experimental finetune based on the Llama3.1 8B Supernova with it's primary goal to be "Short and Sweet" as such, i finetuned the model for 2 epochs on OpenCAI Sharegpt converted dataset and the RP-logs datasets in a effort to achieve this, This version of Control has been finetuned with DPO to help improve the smart's and coherency which was a flaw noticed in the previous model.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Control-8B-V1.1.Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Control-8B-V1.1.Q4_K_M.gguf
|
||||
sha256: 01375fe20999134d6c6330ad645cde07883dcb7113eaef097df6ccff88c56ecf
|
||||
uri: huggingface://QuantFactory/Control-8B-V1.1-GGUF/Control-8B-V1.1.Q4_K_M.gguf
|
||||
- &deepseek
|
||||
## Deepseek
|
||||
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"
|
||||
|
Loading…
Reference in New Issue
Block a user