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-patronus-lynx-70b-instruct (#2788)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-12 18:08:21 +02:00 committed by GitHub
parent 8c08643c65
commit 6886e4e5ab
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

@ -2693,6 +2693,21 @@
- filename: HaloMaidRP-v1.33-15B-L3.i1-Q4_K_M.gguf
sha256: 94d0bf2de4df7e5a11b9ca4db3518d7d22c6fa062d1ee16e4db52b2bb26bc8b3
uri: huggingface://mradermacher/HaloMaidRP-v1.33-15B-L3-i1-GGUF/HaloMaidRP-v1.33-15B-L3.i1-Q4_K_M.gguf
- !!merge <<: *llama3
name: "llama-3-patronus-lynx-70b-instruct"
urls:
- https://huggingface.co/PatronusAI/Llama-3-Patronus-Lynx-70B-Instruct
- https://huggingface.co/mradermacher/Llama-3-Patronus-Lynx-70B-Instruct-GGUF
description: |
Lynx is an open-source hallucination evaluation model. Patronus-Lynx-70B-Instruct was trained on a mix of datasets including CovidQA, PubmedQA, DROP, RAGTruth. The datasets contain a mix of hand-annotated and synthetic data. The maximum sequence length is 8000 tokens.
Model
overrides:
parameters:
model: Llama-3-Patronus-Lynx-70B-Instruct.Q4_K_M.gguf
files:
- filename: Llama-3-Patronus-Lynx-70B-Instruct.Q4_K_M.gguf
sha256: 95a02b71baff287bd84188fc1babcf9dfae25c315e2613391e694cf944f1e5b3
uri: huggingface://mradermacher/Llama-3-Patronus-Lynx-70B-Instruct-GGUF/Llama-3-Patronus-Lynx-70B-Instruct.Q4_K_M.gguf
- &chatml
### ChatML
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"