From 12a2a10cd2a37abf9617fcc0ed70cb0cfc3a7f43 Mon Sep 17 00:00:00 2001
From: mudler <2420543+mudler@users.noreply.github.com>
Date: Tue, 4 Aug 2026 01:51:57 +0000
Subject: [PATCH 1/2] chore(model gallery): :robot: add new models via gallery
 agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
---
 gallery/index.yaml | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index da5ace0a0653..2881b6792704 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,48 @@
 ---
+- name: "deepseek-v4-flash-0731"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF
+  description: |
+    # DeepSeek-V4-Flash-0731
+
+    Technical Report👁️
+
+    ## Introduction
+
+    **DeepSeek-V4-Flash-0731** is the official release of **DeepSeek-V4-Flash**, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.
+
+    DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.
+
+    Notes:
+
+    1. For the Code Agent tasks among the public benchmarks above, DeepSeek-V4-Flash-0731 is evaluated with the minimal mode of DeepSeek Harness (to be released) as the agent framework, using the `max` reasoning effort level with `temperature = 1.0, top_p = 0.95`.
+    2. † DSBench-FullStack is an internal full-stack development test set; DSBench-Hard is an internal test set of difficult coding-agent problems.
+
+    ## Chat Template
+
+    ...
+  license: "mit"
+  tags:
+    - llm
+    - gguf
+    - deepseek
+  icon: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg
+  overrides:
+    backend: ds4
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    parameters:
+      model: ds4flash.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: ds4flash.gguf
+      sha256: ""
+      uri: https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF
 - &nemotron-3-embed-1b
   name: "nemotron-3-embed-1b-q4"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"

From 24d79e814d71fe1aa7db17dbd3a1ff6b43c4a541 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Tue, 4 Aug 2026 13:12:02 +0000
Subject: [PATCH 2/2] fix(gallery): remove duplicate DeepSeek V4 entry

The gallery already contains a complete, checksummed DeepSeek V4 Flash 0731 entry. Remove the generated duplicate whose repository-page URI and empty checksum cannot install a model.

Assisted-by: Codex:gpt-5 [Codex]
---
 gallery/index.yaml | 44 --------------------------------------------
 1 file changed, 44 deletions(-)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 2881b6792704..da5ace0a0653 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,48 +1,4 @@
 ---
-- name: "deepseek-v4-flash-0731"
-  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
-  urls:
-    - https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF
-  description: |
-    # DeepSeek-V4-Flash-0731
-
-    Technical Report👁️
-
-    ## Introduction
-
-    **DeepSeek-V4-Flash-0731** is the official release of **DeepSeek-V4-Flash**, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.
-
-    DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.
-
-    Notes:
-
-    1. For the Code Agent tasks among the public benchmarks above, DeepSeek-V4-Flash-0731 is evaluated with the minimal mode of DeepSeek Harness (to be released) as the agent framework, using the `max` reasoning effort level with `temperature = 1.0, top_p = 0.95`.
-    2. † DSBench-FullStack is an internal full-stack development test set; DSBench-Hard is an internal test set of difficult coding-agent problems.
-
-    ## Chat Template
-
-    ...
-  license: "mit"
-  tags:
-    - llm
-    - gguf
-    - deepseek
-  icon: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg
-  overrides:
-    backend: ds4
-    function:
-      grammar:
-        disable: true
-    known_usecases:
-      - chat
-    parameters:
-      model: ds4flash.gguf
-    template:
-      use_tokenizer_template: true
-  files:
-    - filename: ds4flash.gguf
-      sha256: ""
-      uri: https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF
 - &nemotron-3-embed-1b
   name: "nemotron-3-embed-1b-q4"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"