dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

chore(model gallery): add nvidia_openmath-nemotron-14b-kaggle

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-28 19:44:34 +02:00
parent 978ee96fd3
commit 5e9217703d
1 changed files with 16 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

16
gallery/index.yaml
View file

@ -6281,6 +6281,22 @@
- filename: nvidia_OpenMath-Nemotron-14B-Q4_K_M.gguf
sha256: 2abeccea53899b81cea11fd84fe458d673783f68e7790489fff5c295da6d8026
uri: huggingface://bartowski/nvidia_OpenMath-Nemotron-14B-GGUF/nvidia_OpenMath-Nemotron-14B-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "nvidia_openmath-nemotron-14b-kaggle"
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/1613114437487-60262a8e0703121c822a80b6.png
urls:
- https://huggingface.co/nvidia/OpenMath-Nemotron-14B-Kaggle
- https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-14B-Kaggle-GGUF
description: |
OpenMath-Nemotron-14B-Kaggle is created by finetuning Qwen/Qwen2.5-14B on a subset of OpenMathReasoning dataset. This model was used in our first place submission to the AIMO-2 Kaggle competition!
OpenMath-Nemotron models achieve state-of-the-art results on popular mathematical benchmarks. We present metrics as pass@1 (maj@64) where pass@1 is an average accuracy across 64 generations and maj@64 is the result of majority voting. Please see our paper for more details on the evaluation setup.
overrides:
parameters:
model: nvidia_OpenMath-Nemotron-14B-Kaggle-Q4_K_M.gguf
files:
- filename: nvidia_OpenMath-Nemotron-14B-Kaggle-Q4_K_M.gguf
sha256: 5923990d2699b8dcbefd1fe7bf7406b76f9e3cfa271af93cb870d19d7cd63177
uri: huggingface://bartowski/nvidia_OpenMath-Nemotron-14B-Kaggle-GGUF/nvidia_OpenMath-Nemotron-14B-Kaggle-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578