chore(model gallery): add nvidia_aceinstruct-1.5b (#4819)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-02-13 09:33:40 +01:00 committed by GitHub
parent bf44319d0d
commit f3c27e0381
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -3717,6 +3717,21 @@
- filename: simplescaling_s1.1-32B-Q4_K_M.gguf
sha256: 6ce3cbfcca8ab50a6e877e6bdfc6538c54e1d9a7e5cc81a9930d5d056a9db4e8
uri: huggingface://bartowski/simplescaling_s1.1-32B-GGUF/simplescaling_s1.1-32B-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "nvidia_aceinstruct-1.5b"
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/1613114437487-60262a8e0703121c822a80b6.png
urls:
- https://huggingface.co/nvidia/AceInstruct-1.5B
- https://huggingface.co/bartowski/nvidia_AceInstruct-1.5B-GGUF
description: |
We introduce AceInstruct, a family of advanced SFT models for coding, mathematics, and general-purpose tasks. The AceInstruct family, which includes AceInstruct-1.5B, 7B, and 72B, is Improved using Qwen. These models are fine-tuned on Qwen2.5-Base using general SFT datasets. These same datasets are also used in the training of AceMath-Instruct. Different from AceMath-Instruct which is specialized for math questions, AceInstruct is versatile and can be applied to a wide range of domains. Benchmark evaluations across coding, mathematics, and general knowledge tasks demonstrate that AceInstruct delivers performance comparable to Qwen2.5-Instruct.
overrides:
parameters:
model: nvidia_AceInstruct-1.5B-Q4_K_M.gguf
files:
- filename: nvidia_AceInstruct-1.5B-Q4_K_M.gguf
sha256: 103b7fa617d2b3c2d6e168a878b9b5e3710d19d178bf4b890acf0fac2abafadb
uri: huggingface://bartowski/nvidia_AceInstruct-1.5B-GGUF/nvidia_AceInstruct-1.5B-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578