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 llama3-turbcat-instruct-8b (#2687)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-30 14:40:01 +02:00 committed by GitHub
parent 83d867ad46
commit b7ff441cc0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
gallery/index.yaml
View File

@ -1330,6 +1330,21 @@
- filename: llama3-8B-DarkIdol-2.1-Uncensored-1048K-Q4_K_M-imat.gguf
sha256: 86f0f1e10fc315689e09314aebb7354bb40d8fe95de008d21a75dc8fff1cd2fe
uri: huggingface://LWDCLS/llama3-8B-DarkIdol-2.1-Uncensored-1048K-GGUF-IQ-Imatrix-Request/llama3-8B-DarkIdol-2.1-Uncensored-1048K-Q4_K_M-imat.gguf
- !!merge <<: *llama3
name: "llama3-turbcat-instruct-8b"
urls:
- https://huggingface.co/turboderp/llama3-turbcat-instruct-8b
- https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF
icon: https://huggingface.co/turboderp/llama3-turbcat-instruct-8b/resolve/main/8.png
description: |
This is a direct upgrade over cat 70B, with 2x the dataset size(2GB-> 5GB), added Chinese support with quality on par with the original English dataset. The medical COT portion of the dataset has been sponsored by steelskull, and the action packed character play portion was donated by Gryphe's(aesir dataset). Note that 8b is based on llama3 with limited Chinese support due to base model choice. The chat format in 8b is llama3. The 72b has more comprehensive Chinese support and the format will be chatml.
overrides:
parameters:
model: llama3-turbcat-instruct-8b-Q4_K_M.gguf
files:
- filename: llama3-turbcat-instruct-8b-Q4_K_M.gguf
sha256: a9a36e3220d901a8ad80c75608a81aaeed3a9cdf111247462bf5e3443aad5461
uri: huggingface://bartowski/llama3-turbcat-instruct-8b-GGUF/llama3-turbcat-instruct-8b-Q4_K_M.gguf
- &dolphin
name: "dolphin-2.9-llama3-8b"
url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master"