dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 18:45:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

chore(model gallery): add microsoft_phi-4-reasoning-plus (#5295)

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-05-02 09:43:38 +02:00 • committed by GitHub
parent e7f3effea1
commit 7b3ceb19bb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

14
gallery/index.yaml
View file

@ -1122,6 +1122,20 @@
- filename: microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf - filename: microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf
sha256: ce8becd58f350d8ae0ec3bbb201ab36f750ffab17ab6238f39292d12ab68ea06 sha256: ce8becd58f350d8ae0ec3bbb201ab36f750ffab17ab6238f39292d12ab68ea06
uri: huggingface://bartowski/microsoft_Phi-4-mini-reasoning-GGUF/microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf uri: huggingface://bartowski/microsoft_Phi-4-mini-reasoning-GGUF/microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf
- !!merge <<: *phi4
name: "microsoft_phi-4-reasoning-plus"
urls:
- https://huggingface.co/microsoft/Phi-4-reasoning-plus
- https://huggingface.co/bartowski/microsoft_Phi-4-reasoning-plus-GGUF
description: |
Phi-4-reasoning-plus is a state-of-the-art open-weight reasoning model finetuned from Phi-4 using supervised fine-tuning on a dataset of chain-of-thought traces and reinforcement learning. The supervised fine-tuning dataset includes a blend of synthetic prompts and high-quality filtered data from public domain websites, focused on math, science, and coding skills as well as alignment data for safety and Responsible AI. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning. Phi-4-reasoning-plus has been trained additionally with Reinforcement Learning, hence, it has higher accuracy but generates on average 50% more tokens, thus having higher latency.
overrides:
parameters:
model: microsoft_Phi-4-reasoning-plus-Q4_K_M.gguf
files:
- filename: microsoft_Phi-4-reasoning-plus-Q4_K_M.gguf
sha256: fcb2cdd14881e20613f56d37f49d0c73ec6c00f9bb4d0e4b161a1621d8517f47
uri: huggingface://bartowski/microsoft_Phi-4-reasoning-plus-GGUF/microsoft_Phi-4-reasoning-plus-Q4_K_M.gguf
- &falcon3 - &falcon3
name: "falcon3-1b-instruct" name: "falcon3-1b-instruct"
url: "github:mudler/LocalAI/gallery/falcon3.yaml@master" url: "github:mudler/LocalAI/gallery/falcon3.yaml@master"