chore(model gallery): 🤖 add 0 new models via gallery agent

gallery-agent-summary.json

@@ -0,0 +1,13 @@
+{
+  "search_term": "GGUF",
+  "total_found": 15,
+  "models_added": 1,
+  "added_model_ids": [
+    "mradermacher/Poppy_Porpoise-L3-8B-i1-GGUF"
+  ],
+  "added_model_urls": [
+    "https://huggingface.co/mradermacher/Poppy_Porpoise-L3-8B-i1-GGUF"
+  ],
+  "quantization": "Q4_K_M",
+  "processing_time": "3h6m54.512945498s"
+}

gallery/index.yaml

@@ -3295,7 +3295,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3313,7 +3313,7 @@
   description: |
     google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
   overrides:
     #mmproj: gemma-3-12b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-12b-it-Q4_K_M.gguf
   files:
@@ -3331,7 +3331,7 @@
   description: |
     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
   overrides:
     #mmproj: gemma-3-4b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-4b-it-Q4_K_M.gguf
   files:
@@ -6949,7 +6949,7 @@
       sha256: 2756551de7d8ff7093c2c5eec1cd00f1868bc128433af53f5a8d434091d4eb5a
       uri: huggingface://Triangle104/Nano_Imp_1B-Q8_0-GGUF/nano_imp_1b-q8_0.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
   license: apache-2.0
@@ -23139,3 +23139,40 @@
     - filename: Maenad-70B.i1-Q4_K_M.gguf
       sha256: dd5615ba1ab4ce2a3614afd547e0457fc14c7182de0d2e5f80d84323ee53ec1f
       uri: huggingface://mradermacher/Maenad-70B-i1-GGUF/Maenad-70B.i1-Q4_K_M.gguf
+- !!merge <<: *smollm3
+  name: "poppy_porpoise-l3-8b-i1"
+  urls:
+    - https://huggingface.co/mradermacher/Poppy_Porpoise-L3-8B-i1-GGUF
+  description: |
+    <think>
+    Okay, the user wants a clear and concise description of the model from the repository mradermacher/Poppy_Porpoise-L3-8B-i1-GGUF. They mentioned that this is a quantized version, so I need to focus on the base model.
+
+    Looking at the readme, the base model is Nitral-Archive/Poppy_Porpoise-L3-8B. The quantized version here is likely a GGUF file, which is a format for quantized models. The readme lists various quantization types and their qualities, like IQ1, IQ2, IQ3, etc. The best quality seems to be the i1-Q4_K_M, which is 5.0 GB and recommended.
+
+    The model is an 8B (8 billion parameters) language model. The quantization is probably done for efficiency, making it suitable for devices with limited resources. The readme also mentions that the base model is from Nitral-Archive, so I should credit them. The model is in English and has a license of "other," but the exact terms aren't specified here.
+
+    The user wants this description for a model gallery, so it should be brief but informative. I need to highlight the base model, the quantization details, the size, and the recommended quantization. Also, mention that it's a large language model with a focus on efficiency and performance. Avoid technical jargon but keep it accurate. Make sure to note that the base model is different from the quantized version provided here.
+    </think>
+
+    The model in question is a quantized version of the **Poppy_Porpoise-L3-8B** large language model, originally authored by **Nitral-Archive**. The quantized version (available here) is optimized for efficiency, with a recommended quantization type of **i1-Q4_K_M** (5.0 GB), balancing speed and quality. It is designed for use in resource-constrained environments while retaining the original model's capabilities. The base model, Nitral-Archive/Poppy_Porpoise-L3-8B, is a large-scale language model with a focus on performance and flexibility, though this quantized version is not the original author's work.
+  overrides:
+    parameters:
+      model: Poppy_Porpoise-L3-8B.i1-Q4_K_M.gguf
+    name: Poppy_Porpoise-L3-8B-i1-GGUF
+    backend: llama-cpp
+    template:
+      use_tokenizer_template: true
+    known_usecases:
+    - chat
+    function:
+      grammar:
+        disable: true
+    description: Imported from https://huggingface.co/mradermacher/Poppy_Porpoise-L3-8B-i1-GGUF
+    options:
+    - use_jinja:true
+
+  files:
+    - filename: Poppy_Porpoise-L3-8B.i1-Q4_K_M.gguf
+      sha256: 18808f35209905bac5c097340c1b87e035db9b463c23fbcfd6f4eb2bae176b06
+      uri: https://huggingface.co/mradermacher/Poppy_Porpoise-L3-8B-i1-GGUF/resolve/main/Poppy_Porpoise-L3-8B.i1-Q4_K_M.gguf
+