models(gallery): add l3.1-8b-llamoutcast-i1 (#3047)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-29 20:15:53 +02:00 committed by GitHub
parent 6f8d6f601a
commit 4700c9df92
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -158,6 +158,26 @@
- filename: Sekhmet_Aleph-L3.1-8B-v0.1.i1-Q4_K_M.gguf
sha256: 5b6f4eaa2091bf13a2b563a54a3f87b22efa7f2862362537c956c70da6e11cea
uri: huggingface://mradermacher/Sekhmet_Aleph-L3.1-8B-v0.1-i1-GGUF/Sekhmet_Aleph-L3.1-8B-v0.1.i1-Q4_K_M.gguf
- !!merge <<: *llama31
name: "l3.1-8b-llamoutcast-i1"
icon: https://files.catbox.moe/ecgn0m.jpg
urls:
- https://huggingface.co/Envoid/L3.1-8B-Llamoutcast
- https://huggingface.co/mradermacher/L3.1-8B-Llamoutcast-i1-GGUF
description: |
Warning: this model is utterly cursed.
Llamoutcast
This model was originally intended to be a DADA finetune of Llama-3.1-8B-Instruct but the results were unsatisfactory. So it received some additional finetuning on a rawtext dataset and now it is utterly cursed.
It responds to Llama-3 Instruct formatting.
overrides:
parameters:
model: L3.1-8B-Llamoutcast.i1-Q4_K_M.gguf
files:
- filename: L3.1-8B-Llamoutcast.i1-Q4_K_M.gguf
sha256: 438ca0a7e9470f5ee40f3b14dc2da41b1cafc4ad4315dead3eb57924109d5cf6
uri: huggingface://mradermacher/L3.1-8B-Llamoutcast-i1-GGUF/L3.1-8B-Llamoutcast.i1-Q4_K_M.gguf
## Uncensored models
- !!merge <<: *llama31
name: "darkidol-llama-3.1-8b-instruct-1.0-uncensored-i1"