chore(model gallery): add nvidia_openmath-nemotron-32b (#5260)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-28 19:36:57 +02:00 committed by GitHub
parent 88857696d4
commit 8cba990edc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -6217,6 +6217,22 @@
- filename: pictor-1338-qwenp-1.5b-q8_0.gguf
sha256: 22d2f5b2322d9a354d8578475a6924c2173a913a1e2fa0ec2655f2f5937f6f26
uri: huggingface://adriey/Pictor-1338-QwenP-1.5B-Q8_0-GGUF/pictor-1338-qwenp-1.5b-q8_0.gguf
- !!merge <<: *qwen25
name: "nvidia_openmath-nemotron-32b"
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/1613114437487-60262a8e0703121c822a80b6.png
urls:
- https://huggingface.co/nvidia/OpenMath-Nemotron-32B
- https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-32B-GGUF
description: |
OpenMath-Nemotron-32B is created by finetuning Qwen/Qwen2.5-32B on OpenMathReasoning dataset. This model is ready for commercial use.
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-32B-Q4_K_M.gguf
files:
- filename: nvidia_OpenMath-Nemotron-32B-Q4_K_M.gguf
sha256: 91d1f53204ff47e49093ea0e4a6dae656fd79d9cdb23a50627bc6028396f5ab4
uri: huggingface://bartowski/nvidia_OpenMath-Nemotron-32B-GGUF/nvidia_OpenMath-Nemotron-32B-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578