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

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
@@ -23023,3 +23023,33 @@
     - filename: Evilmind-24B-v1.i1-Q4_K_M.gguf
       sha256: 22e56c86b4f4a8f7eb3269f72a6bb0f06a7257ff733e21063fdec6691a52177d
       uri: huggingface://mradermacher/Evilmind-24B-v1-i1-GGUF/Evilmind-24B-v1.i1-Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "lmunit-llama3.1-70b"
+  urls:
+    - https://huggingface.co/mradermacher/LMUnit-llama3.1-70b-GGUF
+  description: |
+    **Model Name:** LMUnit-llama3.1-70b
+    **Base Model:** Meta's Llama-3.1-70B-Instruct
+    **Developed By:** Contextual AI
+    **Model Type:** Fine-tuned language model for fine-grained, natural language-based evaluation of AI responses
+    **Primary Use Case:** Evaluating the quality of model outputs using unit tests (e.g., accuracy, relevance, safety, structure) via human-like judgment
+
+    **Key Features:**
+    - Trained on multi-objective signals (pairwise comparisons, direct ratings, criterion-specific feedback)
+    - Generates continuous scores (1–5) indicating how well a response satisfies a given unit test
+    - Achieves state-of-the-art performance on evaluation benchmarks: **FLASK (72.03)**, **BiGGen-Bench (67.69)**, and **RewardBench (93.5% accuracy)**
+    - Highly aligned with human preferences, ranking in the top 5 of RewardBench and top 2 on RewardBench2
+    - Designed to support nuanced, scenario-specific evaluations of long-form and complex outputs
+
+    **Ideal For:** Researchers and developers building systems that require precise, interpretable, and human-aligned evaluation of LLM outputs — especially in testing, benchmarking, and alignment pipelines.
+
+    **Paper:** [LMUnit: Fine-grained Evaluation with Natural Language Unit Tests](https://arxiv.org/abs/2412.13091)
+    **GitHub:** [ContextualAI/LMUnit](https://github.com/ContextualAI/LMUnit)
+    **Hugging Face:** [ContextualAI/LMUnit-llama3.1-70b](https://huggingface.co/ContextualAI/LMUnit-llama3.1-70b)
+  overrides:
+    parameters:
+      model: LMUnit-llama3.1-70b.Q4_K_S.gguf
+  files:
+    - filename: LMUnit-llama3.1-70b.Q4_K_S.gguf
+      sha256: 59b192396784ed498d00ef96091b0e128ce6ed42f28d1669aa3d3e21720f6a2e
+      uri: huggingface://mradermacher/LMUnit-llama3.1-70b-GGUF/LMUnit-llama3.1-70b.Q4_K_S.gguf