chore(model gallery): 🤖 add 1 new models via gallery agent

gallery/index.yaml

@@ -3127,7 +3127,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3145,7 +3145,7 @@
   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:
@@ -3163,7 +3163,7 @@
   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:
@@ -6781,7 +6781,7 @@
       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
@@ -22950,3 +22950,29 @@
     - filename: apollo-astralis-4b.i1-Q4_K_M.gguf
       sha256: 94e1d371420b03710fc7de030c1c06e75a356d9388210a134ee2adb4792a2626
       uri: huggingface://mradermacher/apollo-astralis-4b-i1-GGUF/apollo-astralis-4b.i1-Q4_K_M.gguf
+- !!merge <<: *llama33
+  name: "llama-33-nemotron-super-49b-v15-bias-injections-reduced"
+  urls:
+    - https://huggingface.co/mradermacher/Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced-GGUF
+  description: |
+    The **Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced** is a large language model based on the Llama-33 architecture, developed and fine-tuned by **hirundo-io**. It is a high-capacity, 49-billion-parameter model optimized for advanced natural language understanding and generation, with a focus on reducing bias through targeted injection techniques during training. The model is trained on a diverse and extensive dataset, making it suitable for complex tasks such as reasoning, code generation, and content creation.
+
+    This version is a **reduced-bias variant** of the original Nemotron-Super series, engineered to minimize harmful or skewed outputs while maintaining strong performance. It was fine-tuned using advanced techniques to improve fairness and alignment with ethical guidelines.
+
+    While the model is available in multiple quantized GGUF formats (e.g., Q4_K_S, Q6_K, Q8_0) for efficient inference on consumer hardware, the original, unquantized version is hosted at [hirundo-io/Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced](https://huggingface.co/hirundo-io/Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced) and is intended for research, development, and production use where full precision is required.
+
+    **Key Features:**
+    - 49B parameters (large-scale, high performance)
+    - Fine-tuned for reduced bias and improved ethical alignment
+    - Based on Llama-33 architecture (derived from Meta's Llama family)
+    - Compatible with Hugging Face `transformers` library
+    - Available in multiple GGUF quantizations for efficient deployment
+
+    Ideal for developers, researchers, and enterprises seeking a powerful, ethically enhanced LLM with strong reasoning and generation capabilities.
+  overrides:
+    parameters:
+      model: Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced.Q4_K_M.gguf
+  files:
+    - filename: Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced.Q4_K_M.gguf
+      sha256: d21a42090987912f9fabb6e8061e8264e6072dcf8f25b63990cfe1618166ec65
+      uri: huggingface://mradermacher/Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced-GGUF/Llama-33-Nemotron-Super-49B-v15-bias-injections-reduced.Q4_K_M.gguf