From 9ac61f271c036094ccd1e08eefeefeccea6faf63 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Sun, 20 Sep 2026 08:05:27 +0000
Subject: [PATCH] fix(gallery): set MiniCPM5 context at the top level

The Q4 and Q8 overrides place context_size inside parameters, where
PredictionOptions ignores it. Move it beside parameters so both
builds use the intended 8,192-token context, matching F16.

Assisted-by: Codex:GPT-6
---
 docs/content/features/model-gallery.md | 3 ++-
 gallery/index.yaml                     | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md
index bc8e524c6..89756bf16 100644
--- a/docs/content/features/model-gallery.md
+++ b/docs/content/features/model-gallery.md
@@ -104,7 +104,8 @@ local-ai models install minicpm5-2b --variant minicpm5-2b-f16
 ```
 
 The F16 weights require a 5.04 GB download, plus additional memory for inference.
-This entry uses the embedded chat template and an 8,192-token context.
+All three builds use the embedded chat template and an 8,192-token default context.
+To change the context in a model configuration, set `context_size` at the top level, alongside `parameters`.
 See the [official GGUF repository](https://huggingface.co/openbmb/MiniCPM5-2B-GGUF).
 
 ## VRAM and download size estimates
diff --git a/gallery/index.yaml b/gallery/index.yaml
index 92832226e..8aa919a69 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -27748,6 +27748,7 @@
     - model: minicpm5-2b-f16
   overrides:
     backend: llama-cpp
+    context_size: 8192
     known_usecases:
       - chat
     options:
@@ -27756,7 +27757,6 @@
       use_tokenizer_template: true
     parameters:
       model: llama-cpp/models/minicpm5-2b/MiniCPM5-2B-Q4_K_M.gguf
-      context_size: 8192
       temperature: 1.0
       top_p: 0.95
   files:
@@ -27772,6 +27772,7 @@
   variants: null
   overrides:
     backend: llama-cpp
+    context_size: 8192
     known_usecases:
       - chat
     options:
@@ -27780,7 +27781,6 @@
       use_tokenizer_template: true
     parameters:
       model: llama-cpp/models/minicpm5-2b/MiniCPM5-2B-Q8_0.gguf
-      context_size: 8192
       temperature: 1.0
       top_p: 0.95
   files: