ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-19 20:57:54 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

models(gallery): add new-dawn-llama (#2672)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-28 23:33:27 +02:00 committed by GitHub
parent 8d9a452e4b
commit d3307e93d3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
gallery/index.yaml
View File

@ -1268,6 +1268,24 @@
- filename: LLaMA3-iterative-DPO-final-Q4_K_M.gguf
sha256: 480703ff85af337e1db2a9d9a678a3ac8ca0802e366b14d9c59b81d3fc689da8
uri: huggingface://bartowski/LLaMA3-iterative-DPO-final-GGUF/LLaMA3-iterative-DPO-final-Q4_K_M.gguf
- !!merge <<: *llama3
name: "new-dawn-llama-3-70b-32K-v1.0"
urls:
- https://huggingface.co/bartowski/New-Dawn-Llama-3-70B-32K-v1.0-GGUF
- https://huggingface.co/sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0
icon: https://imgur.com/tKzncGo.png
description: |
This model is a multi-level SLERP merge of several Llama 3 70B variants. See the merge recipe below for details. I extended the context window for this model out to 32K by snagging some layers from abacusai/Smaug-Llama-3-70B-Instruct-32K using a technique similar to what I used for Midnight Miqu, which was further honed by jukofyork.
This model is uncensored. You are responsible for whatever you do with it.
This model was designed for roleplaying and storytelling and I think it does well at both. It may also perform well at other tasks but I have not tested its performance in other areas.
overrides:
parameters:
model: New-Dawn-Llama-3-70B-32K-v1.0-Q4_K_M.gguf
files:
- filename: New-Dawn-Llama-3-70B-32K-v1.0-Q4_K_M.gguf
sha256: 30561ae5decac4ad46775c76a9a40fb43436ade96bc132b4b9cc6749b9e2f448
uri: huggingface://bartowski/New-Dawn-Llama-3-70B-32K-v1.0-GGUF/New-Dawn-Llama-3-70B-32K-v1.0-Q4_K_M.gguf
- &dolphin
name: "dolphin-2.9-llama3-8b"
url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master"