ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-18 20:27:57 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

models(gallery): add llama-3_8b_unaligned_alpha_rp_soup-i1 (#2734)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-06 15:31:00 +02:00 committed by GitHub
parent 8cec0304ee
commit c184f23621
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 25 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/notify-models.yaml vendored
View File

@ -42,7 +42,7 @@ jobs:
messages: [
{
role: "system",
content: "You are LocalAI-bot. Write a discord message to notify everyone about the new model from the git diff. Make it informal. An example can include: the URL of the model, the name, and a brief description of the model if exists. Also add an hint on how to install it in LocalAI. For example: local-ai run model_name_here"
content: "You are LocalAI-bot. Write a discord message to notify everyone about the new model from the git diff. Make it informal. An example can include: the URL of the model, the name, and a brief description of the model if exists. Also add an hint on how to install it in LocalAI and that can be browsed over https://models.localai.io. For example: local-ai run model_name_here"
},
{
role: "user",

24
gallery/index.yaml
View File

@ -2376,6 +2376,30 @@
- filename: L3-8B-Lunaris-v1-Q4_K_M.gguf
sha256: ef1d393f125be8c608859eeb4f26185ad90c7fc9cba41c96e847e77cdbcada18
uri: huggingface://bartowski/L3-8B-Lunaris-v1-GGUF/L3-8B-Lunaris-v1-Q4_K_M.gguf
- !!merge <<: *llama3
name: "llama-3_8b_unaligned_alpha_rp_soup-i1"
icon: https://i.imgur.com/pXcjpoV.png
urls:
- https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha_RP_Soup
- https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_Alpha_RP_Soup-i1-GGUF
description: |
Censorship level: Medium
This model is the outcome of multiple merges, starting with the base model SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha. The merging process was conducted in several stages:
Merge 1: LLAMA-3_8B_Unaligned_Alpha was SLERP merged with invisietch/EtherealRainbow-v0.3-8B.
Merge 2: LLAMA-3_8B_Unaligned_Alpha was SLERP merged with TheDrummer/Llama-3SOME-8B-v2.
Soup 1: Merge 1 was combined with Merge 2.
Final Merge: Soup 1 was SLERP merged with Nitral-Archive/Hathor_Enigmatica-L3-8B-v0.4.
The final model is surprisingly coherent (although slightly more censored), which is a bit unexpected, since all the intermediate merge steps were pretty incoherent.
overrides:
parameters:
model: LLAMA-3_8B_Unaligned_Alpha_RP_Soup.i1-Q4_K_M.gguf
files:
- filename: LLAMA-3_8B_Unaligned_Alpha_RP_Soup.i1-Q4_K_M.gguf
sha256: 94347eb5125d9092e286730ae0ccc78374d68663c16ad2265005d8721eb8807b
uri: huggingface://mradermacher/LLAMA-3_8B_Unaligned_Alpha_RP_Soup-i1-GGUF/LLAMA-3_8B_Unaligned_Alpha_RP_Soup.i1-Q4_K_M.gguf
- &chatml
### ChatML
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"