fix(gallery): restore entries clobbered by batch PR applies (#12016)

The batch of "gallery: apply PR" commits replayed gallery-agent diffs against a stale base. Each new top-of-file entry overwrote the entry above it instead of being inserted, which lost seven entries: - qwen3.8-27b-uncensored-q4/-q8 (#11705, overwritten by #11909) - qwen3.8-flash-next-uncensored (#11832, overwritten by #11841) - spark-x2.5-4b-q4/-q6/-q8 (#11923, overwritten by #11926) - deepseek-v4-flash-vision-exp (#11873): #11927 renamed its name line to qwopus3.8-27b-flash, which duplicated that entry and failed the "declares every entry name exactly once" gallery lint on master. Each restored entry is identical (YAML-equal) to the one in its PR head. Assisted-by: Claude:claude-opus-5 [Bash] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-10-28 09:08:54 -04:00 · 2026-09-12 23:08:23 +02:00
1 parent 8321234275
commit 0e3ee19ec4
@@ -46,7 +46,68 @@
    - filename: llama-cpp/models/Spark-X2.5-4B-Q4_K_M/Spark-X2.5-4B-Q4_K_M.gguf
      sha256: adfcfa19a4ed6a5985da8bf565fe15f8e1a7e131d79bae2d19d48d1c40109428
      uri: https://huggingface.co/XHToken/Spark-X2.5-4B-GGUF/resolve/main/Spark-X2.5-4B-Q4_K_M.gguf
- name: "qwopus3.8-27b-flash"
+- name: "qwen3.8-flash-next-uncensored"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF
+  description: |
+    # Qwen3.8-Flash-Next
+
+    > [!Note]
+    > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
+    >
+    > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.
+
+    > [!Tip]
+    > For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud.
+    >
+    > In particular, **Qwen3.8-Flash** is the official version based on Qwen3.8-Flash-Next with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-Flash Overview.
+
+    As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we can scale, but how efficiently we can do so. Sustainable progress toward artificial general intelligence (AGI) that benefits everyone demands architectural innovation. Today, we are sharing a concrete step in that direction: Qwen3.8-Flash-Next.
+
+    ...
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - qwen
+    - reasoning
+  icon: https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.8-Flash-Next/architecture.png
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Qwen3.8-Flash-Next-Uncensored-Q4_K_M/mmproj-Qwen3.8-Flash-Next-Uncensored-F16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/Qwen3.8-Flash-Next-Uncensored-Q4_K_M/Qwen3.8-Flash-Next-Uncensored-Q4_K_M-00001-of-00003.gguf
+      presence_penalty: 1.5
+      repeat_penalty: 1
+      temperature: 0.7
+      top_k: 20
+      top_p: 0.8
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwen3.8-Flash-Next-Uncensored-Q4_K_M/Qwen3.8-Flash-Next-Uncensored-Q4_K_M-00001-of-00003.gguf
+      sha256: '****************************************************************'
+      uri: https://huggingface.co/orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF/resolve/main/Qwen3.8-Flash-Next-Uncensored-Q4_K_M-00001-of-00003.gguf
+    - filename: llama-cpp/models/Qwen3.8-Flash-Next-Uncensored-Q4_K_M/Qwen3.8-Flash-Next-Uncensored-Q4_K_M-00002-of-00003.gguf
+      sha256: '****************************************************************'
+      uri: https://huggingface.co/orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF/resolve/main/Qwen3.8-Flash-Next-Uncensored-Q4_K_M-00002-of-00003.gguf
+    - filename: llama-cpp/models/Qwen3.8-Flash-Next-Uncensored-Q4_K_M/Qwen3.8-Flash-Next-Uncensored-Q4_K_M-00003-of-00003.gguf
+      sha256: '****************************************************************'
+      uri: https://huggingface.co/orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF/resolve/main/Qwen3.8-Flash-Next-Uncensored-Q4_K_M-00003-of-00003.gguf
+    - filename: llama-cpp/mmproj/Qwen3.8-Flash-Next-Uncensored-Q4_K_M/mmproj-Qwen3.8-Flash-Next-Uncensored-F16.gguf
+      sha256: '****************************************************************'
+      uri: https://huggingface.co/orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF/resolve/main/mmproj-Qwen3.8-Flash-Next-Uncensored-F16.gguf
+- name: "deepseek-v4-flash-vision-exp"
  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
  urls:
    - https://huggingface.co/unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF
@@ -2228,6 +2289,105 @@
    - filename: llama-cpp/models/Qwen3.8-27B-DFlash2-Q4_K_M/Qwen3.8-27B-DFlash2-Q4_K_M.gguf
      uri: https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/main/Qwen3.8-27B-DFlash2-Q4_K_M.gguf
      sha256: 1a25c56858e1ebe93f2718ac1d49d1151f9323325c1bbfd6209370f4db131ebd
+- &qwen3-8-27b-uncensored
+  name: "qwen3.8-27b-uncensored-q4"
+  variants:
+    - model: qwen3.8-27b-uncensored-q8
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/Qwen/Qwen3.8-27B
+    - https://huggingface.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF
+  description: |
+    Qwen3.8-27B-Uncensored reduces refusal behavior while retaining the base
+    model's text, vision, reasoning, and tool-use capabilities. Its integrated
+    MTP head supports speculative decoding without a separate draft model.
+
+    This default entry uses the Q4_K_M GGUF and F16 vision projector. A
+    higher-quality Q8_0 model is available as a variant.
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+    - reasoning
+    - thinking
+    - tools
+    - vision
+    - multimodal
+    - long-context
+    - uncensored
+    - mtp
+  last_checked: "2026-08-24"
+  overrides:
+    backend: llama-cpp
+    context_size: 262144
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/qwen3.8-27b-uncensored/vision-f16.gguf
+    options:
+      - use_jinja:true
+      - spec_type:draft-mtp
+      - spec_n_max:3
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/qwen3.8-27b-uncensored/Qwen3.8-27B-Uncensored-Q4_K_M.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/qwen3.8-27b-uncensored/Qwen3.8-27B-Uncensored-Q4_K_M.gguf
+      uri: huggingface://JonathanColetti/Qwen3.8-27B-Uncensored-GGUF/Qwen3.8-27B-Uncensored-Q4_K_M.gguf
+      sha256: 4c5e2db039e9325ac7724c8846c71356a24ad1cdfa28002d73ecb6be645f9675
+    - filename: llama-cpp/mmproj/qwen3.8-27b-uncensored/vision-f16.gguf
+      uri: huggingface://JonathanColetti/Qwen3.8-27B-Uncensored-GGUF/Qwen3.8-27B-Uncensored-vision-f16.gguf
+      sha256: 5ac423f8a29059dc24e51bc6a43e9380dcd57a9347f28b62591e0b3f60b7081c
+- !!merge <<: *qwen3-8-27b-uncensored
+  name: "qwen3.8-27b-uncensored-q8"
+  variants: []
+  description: |
+    Qwen3.8-27B-Uncensored in the higher-quality Q8_0 GGUF format, with its
+    integrated MTP head and shared F16 vision projector.
+  overrides:
+    backend: llama-cpp
+    context_size: 262144
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/qwen3.8-27b-uncensored/vision-f16.gguf
+    options:
+      - use_jinja:true
+      - spec_type:draft-mtp
+      - spec_n_max:3
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/qwen3.8-27b-uncensored/Qwen3.8-27B-Uncensored-Q8_0.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/qwen3.8-27b-uncensored/Qwen3.8-27B-Uncensored-Q8_0.gguf
+      uri: huggingface://JonathanColetti/Qwen3.8-27B-Uncensored-GGUF/Qwen3.8-27B-Uncensored-Q8_0.gguf
+      sha256: fb2cb9aa5407264aec6698faf41183f337809352abe0bd8fb750c0b689f4ced2
+    - filename: llama-cpp/mmproj/qwen3.8-27b-uncensored/vision-f16.gguf
+      uri: huggingface://JonathanColetti/Qwen3.8-27B-Uncensored-GGUF/Qwen3.8-27B-Uncensored-vision-f16.gguf
+      sha256: 5ac423f8a29059dc24e51bc6a43e9380dcd57a9347f28b62591e0b3f60b7081c
 - &huihui-qwen3-8-27b
  name: "huihui-qwen3.8-27b-abliterated"
  variants:
@@ -4535,6 +4695,102 @@
      uri: huggingface://XHToken/Spark-X2.5-1.7B-GGUF/Spark-X2.5-1.7B-Q8_0.gguf
      sha256: cd77c03185a834bb1162a4b7713520be5838058bfc54873645beff470bb24442

+- &spark-x2-5-4b
+  name: "spark-x2.5-4b-q4"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  variants:
+    - model: spark-x2.5-4b-q6
+    - model: spark-x2.5-4b-q8
+  urls:
+    - https://huggingface.co/XHToken/Spark-X2.5-4B
+    - https://huggingface.co/abenzerps/Spark-X2.5-4B-GGUF
+  description: |
+    Spark-X2.5-4B is XHToken's 4B text model for conversation, reasoning,
+    coding, and multilingual tasks. This entry uses Q4_K_M GGUF weights;
+    Q6_K and Q8_0 builds are available as variants. All builds use the
+    embedded Jinja chat template and a 32K-token default context.
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - reasoning
+    - coding
+    - multilingual
+  last_checked: "2026-09-08"
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q4_K_M.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: -1
+      min_p: 0
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q4_K_M.gguf
+      uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q4_K_M.gguf
+      sha256: 7934660bfc5b9bf04be0a0ac6179a1d16e1d4331b448857c86b8b2801b3ef72c
+- !!merge <<: *spark-x2-5-4b
+  name: "spark-x2.5-4b-q6"
+  variants: []
+  description: |
+    Spark-X2.5-4B in Q6_K GGUF format, with the embedded Jinja chat
+    template and a 32K-token default context.
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q6_K.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: -1
+      min_p: 0
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q6_K.gguf
+      uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q6_K.gguf
+      sha256: 7293e99081e032b30e481c159aa35b3f7d133a746c1096910024ea71fff82246
+- !!merge <<: *spark-x2-5-4b
+  name: "spark-x2.5-4b-q8"
+  variants: []
+  description: |
+    Spark-X2.5-4B in Q8_0 GGUF format, with the embedded Jinja chat
+    template and a 32K-token default context.
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q8_0.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: -1
+      min_p: 0
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q8_0.gguf
+      uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q8_0.gguf
+      sha256: 58a4fc627cc2b2cbea02f81fb22960938e86bf3e62a2b3ae01c55a678481d46b
 - &qwen3-8-9b
  name: "qwen3.8-9b-q4"
  variants: