mirror of
https://github.com/getumbrel/umbrel-apps.git
synced 2026-11-21 21:44:02 +03:00
Update ollama to v0.30.4
Co-authored-by: Kai Chappel <kaichappel@users.noreply.github.com>
This commit is contained in:
1 parent
d16b52e750
commit
2eebf7b6e2
2 files changed
+4
-3
No files matched your search
@@ -8,7 +8,7 @@ services:
|
||||
PROXY_AUTH_ADD: "false"
|
||||
|
||||
ollama:
|
||||
image: ollama/ollama:0.30.3@sha256:94f691cb4561e28f9be252a95defa5a33c388651fde803ca260576d57f243a57
|
||||
image: ollama/ollama:0.30.4@sha256:7a3fe51cf50e0a6ddbcd054247d160baa90eb1935700bb59f3e96aa9a6da5025
|
||||
environment:
|
||||
OLLAMA_ORIGINS: "*"
|
||||
OLLAMA_CONTEXT_LENGTH: 8192
|
||||
|
||||
@@ -3,7 +3,7 @@ id: ollama
|
||||
name: Ollama
|
||||
tagline: Self-host open source AI models like DeepSeek-R1, Llama, and more
|
||||
category: ai
|
||||
version: "0.30.3"
|
||||
version: "0.30.4"
|
||||
port: 11434
|
||||
description: >-
|
||||
Ollama allows you to download and run advanced AI models directly on your own hardware. Self-hosting AI models ensures full control over your data and protects your privacy.
|
||||
@@ -39,7 +39,8 @@ defaultPassword: ""
|
||||
dependencies: []
|
||||
releaseNotes: >-
|
||||
Key highlights in this release:
|
||||
- Adds support for Gemma 4 12B models
|
||||
- Updates the bundled llama.cpp runtime used for local model inference
|
||||
- Notes a known upstream issue where gemma4:12b may crash with a floating point exception
|
||||
|
||||
|
||||
Full release notes are available at https://github.com/ollama/ollama/releases/
|
||||
|
||||
Reference in new issue
Block a user