ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-02-20 17:32:47 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

models(gallery): add cathallama-70b (#3221)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-08-12 09:59:17 +02:00 committed by GitHub
parent 7137c32f8f
commit 4dfa085339
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 27 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
gallery/index.yaml
View File

@ -502,6 +502,33 @@
- filename: Infinity-Instruct-7M-Gen-Llama3_1-70B.Q4_K_M.gguf
sha256: f4379ab4d7140da0510886073375ca820ea9ac4ad9d3c20e17ed05156bd29697
uri: huggingface://mradermacher/Infinity-Instruct-7M-Gen-Llama3_1-70B-GGUF/Infinity-Instruct-7M-Gen-Llama3_1-70B.Q4_K_M.gguf
- !!merge <<: *llama31
name: "cathallama-70b"
icon: https://cdn-uploads.huggingface.co/production/uploads/649dc85249ae3a68334adcc6/KxaiZ7rDKkYlix99O9j5H.png
urls:
- https://huggingface.co/gbueno86/Cathallama-70B
- https://huggingface.co/mradermacher/Cathallama-70B-GGUF
description: |
Notable Performance
9% overall success rate increase on MMLU-PRO over LLaMA 3.1 70b
Strong performance in MMLU-PRO categories overall
Great performance during manual testing
Creation workflow
Models merged
meta-llama/Meta-Llama-3.1-70B-Instruct
turboderp/Cat-Llama-3-70B-instruct
Nexusflow/Athene-70B
overrides:
parameters:
model: Cathallama-70B.Q4_K_M.gguf
files:
- filename: Cathallama-70B.Q4_K_M.gguf
sha256: 7bbac0849a8da82e7912a493a15fa07d605f1ffbe7337a322f17e09195511022
uri: huggingface://mradermacher/Cathallama-70B-GGUF/Cathallama-70B.Q4_K_M.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"