Sanitized mirror from private repository - 2026-03-18 10:31:50 UTC

2026-03-18 10:31:50 +00:00
commit 8e49624d78
1221 changed files with 304405 additions and 0 deletions
--- a/hosts/synology/atlantis/ollama/model_usage.txt
+++ b/hosts/synology/atlantis/ollama/model_usage.txt
@@ -0,0 +1,17 @@
+Why these models?
+
+Coding:
+
+codegemma:2b → lightweight, good for completions.
+
+codellama:7b → solid for structured code (like Docker Compose).
+
+mistral:7b → generalist, also good with logic in code.
+
+Writing (tech docs & emails):
+
+llama3.2:3b → smaller generalist.
+
+gemma:7b → more natural writing.
+
+neural-chat:7b → conversational, good for email tone.