dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-19 18:15:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

models(gallery): add versatillama-llama-3.2-3b-instruct-abliterated (#3771)

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-10-09 16:58:34 +02:00 • committed by GitHub
parent 759d35e6b5
commit 1a3b3d3e67
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 16 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
gallery/arch-function.yaml
View file

@ -63,4 +63,4 @@ config_file: |
- '<dummy32000>'
- '</s>'
- "<|eot_id|>"
- "<|end_of_text|>"
- "<|end_of_text|>"

15
gallery/index.yaml
View file

@ -100,6 +100,21 @@
- filename: llama-3.2-1b-instruct-q8_0.gguf
sha256: ba345c83bf5cc679c653b853c46517eea5a34f03ed2205449db77184d9ae62a9
uri: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF/llama-3.2-1b-instruct-q8_0.gguf
## Uncensored
- !!merge <<: *llama32
icon: https://cdn-uploads.huggingface.co/production/uploads/66c9d7a26f2335ba288810a4/4YDg-rcEXCK0fdTS1fBzE.webp
name: "versatillama-llama-3.2-3b-instruct-abliterated"
urls:
- https://huggingface.co/QuantFactory/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-GGUF
description: |
Small but Smart Fine-Tuned on Vast dataset of Conversations. Able to Generate Human like text with high performance within its size. It is Very Versatile when compared for it's size and Parameters and offers capability almost as good as Llama 3.1 8B Instruct.
overrides:
parameters:
model: VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K_M.gguf
files:
- filename: VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K_M.gguf
sha256: 15b9e4a987f50d7594d030815c7166a996e20db46fe1e20da03e96955020312c
uri: huggingface://QuantFactory/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-GGUF/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K_M.gguf
- &qwen25
## Qwen2.5
name: "qwen2.5-14b-instruct"