mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-09 12:03:15 +00:00
chore(model gallery): add nvidia_openmath-nemotron-7b (#5262)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
0027681090
commit
3ad5691db6
@ -6249,6 +6249,22 @@
|
||||
- filename: nvidia_OpenMath-Nemotron-1.5B-Q4_K_M.gguf
|
||||
sha256: cdb74247c7918fdb70f9a9aa8217476f2f02e2fff723631255a441eb0db302e2
|
||||
uri: huggingface://bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/nvidia_OpenMath-Nemotron-1.5B-Q4_K_M.gguf
|
||||
- !!merge <<: *qwen25
|
||||
name: "nvidia_openmath-nemotron-7b"
|
||||
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/1613114437487-60262a8e0703121c822a80b6.png
|
||||
urls:
|
||||
- https://huggingface.co/nvidia/OpenMath-Nemotron-7B
|
||||
- https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-7B-GGUF
|
||||
description: |
|
||||
OpenMath-Nemotron-7B is created by finetuning Qwen/Qwen2.5-Math-7B 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-7B-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: nvidia_OpenMath-Nemotron-7B-Q4_K_M.gguf
|
||||
sha256: e205dd86ab9c73614d88dc3a84bd1a4e94255528f9ddb33e739ea23830342ee4
|
||||
uri: huggingface://bartowski/nvidia_OpenMath-Nemotron-7B-GGUF/nvidia_OpenMath-Nemotron-7B-Q4_K_M.gguf
|
||||
- &llama31
|
||||
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
|
||||
icon: https://avatars.githubusercontent.com/u/153379578
|
||||
|
Loading…
x
Reference in New Issue
Block a user