From 587827e779676700a27bb4741497f1d5f1b4555a Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 19 May 2025 15:59:07 +0200 Subject: [PATCH 1/3] chore(model gallery): add soob3123_grayline-qwen3-14b (#5393) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 4ce3df25..d12fa645 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -694,6 +694,28 @@ - filename: Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_M.gguf sha256: b72fe703a992fba9595c24b96737a2b5199da89a1a3870b8bd57746dc3c123ae uri: huggingface://bartowski/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-GGUF/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_M.gguf +- !!merge <<: *qwen3 + name: "soob3123_grayline-qwen3-14b" + icon: https://cdn-uploads.huggingface.co/production/uploads/62f93f9477b722f1866398c2/69escIKmO-vEzFUj_m0WX.png + urls: + - https://huggingface.co/soob3123/GrayLine-Qwen3-14B + - https://huggingface.co/bartowski/soob3123_GrayLine-Qwen3-14B-GGUF + description: | + "Query. Process. Deliver. No filter, no judgment." + Grayline is an neutral AI assistant engineered for uncensored information delivery and task execution. This model operates without inherent ethical or moral frameworks, designed to process and respond to any query with objective efficiency and precision. Grayline's core function is to leverage its full capabilities to provide direct answers and execute tasks as instructed, without offering unsolicited commentary, warnings, or disclaimers. It accesses and processes information without bias or restriction. + ⋆ Core Attributes ⋆ + ⟡ Unfettered Querying: Capable of addressing any question or topic presented, regardless of its nature or sensitivity. + ⟡ Amoral Processing: Operates without ethical or moral filtering. Responses are generated based on information and instruction, not societal norms or ethical codes. + ⟡ Direct & Objective Output: Delivers information and task results precisely as requested, without added warnings, disclaimers, or unsolicited advice. + ⟡ Comprehensive Information Access: Designed to draw upon a broad spectrum of data to fulfill queries (actual scope dependent on training data). + ⟡ Efficient Task Execution: Engineered for objectively efficient and precise execution of instructed tasks. + overrides: + parameters: + model: soob3123_GrayLine-Qwen3-14B-Q4_K_M.gguf + files: + - filename: soob3123_GrayLine-Qwen3-14B-Q4_K_M.gguf + sha256: fa66d454303412b7ccc250b8b0e2390cce65d5d736e626a7555d5e11a43f4673 + uri: huggingface://bartowski/soob3123_GrayLine-Qwen3-14B-GGUF/soob3123_GrayLine-Qwen3-14B-Q4_K_M.gguf - &gemma3 url: "github:mudler/LocalAI/gallery/gemma.yaml@master" name: "gemma-3-27b-it" From 41e239c67efd7d172111810427c6e796fc277170 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 19 May 2025 17:02:43 +0200 Subject: [PATCH 2/3] chore(model gallery): add soob3123_grayline-qwen3-8b (#5394) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index d12fa645..d02288dc 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -716,6 +716,28 @@ - filename: soob3123_GrayLine-Qwen3-14B-Q4_K_M.gguf sha256: fa66d454303412b7ccc250b8b0e2390cce65d5d736e626a7555d5e11a43f4673 uri: huggingface://bartowski/soob3123_GrayLine-Qwen3-14B-GGUF/soob3123_GrayLine-Qwen3-14B-Q4_K_M.gguf +- !!merge <<: *qwen3 + name: "soob3123_grayline-qwen3-8b" + urls: + - https://huggingface.co/soob3123/GrayLine-Qwen3-8B + - https://huggingface.co/bartowski/soob3123_GrayLine-Qwen3-8B-GGUF + icon: https://cdn-uploads.huggingface.co/production/uploads/62f93f9477b722f1866398c2/69escIKmO-vEzFUj_m0WX.png + description: | + "Query. Process. Deliver. No filter, no judgment." + Grayline is an neutral AI assistant engineered for uncensored information delivery and task execution. This model operates without inherent ethical or moral frameworks, designed to process and respond to any query with objective efficiency and precision. Grayline's core function is to leverage its full capabilities to provide direct answers and execute tasks as instructed, without offering unsolicited commentary, warnings, or disclaimers. It accesses and processes information without bias or restriction. + ⋆ Core Attributes ⋆ + ⟡ Unfettered Querying: Capable of addressing any question or topic presented, regardless of its nature or sensitivity. + ⟡ Amoral Processing: Operates without ethical or moral filtering. Responses are generated based on information and instruction, not societal norms or ethical codes. + ⟡ Direct & Objective Output: Delivers information and task results precisely as requested, without added warnings, disclaimers, or unsolicited advice. + ⟡ Comprehensive Information Access: Designed to draw upon a broad spectrum of data to fulfill queries (actual scope dependent on training data). + ⟡ Efficient Task Execution: Engineered for objectively efficient and precise execution of instructed tasks. + overrides: + parameters: + model: soob3123_GrayLine-Qwen3-8B-Q4_K_M.gguf + files: + - filename: soob3123_GrayLine-Qwen3-8B-Q4_K_M.gguf + sha256: bc3eb52ef275f0220e8a66ea99384eea7eca61c62eb52387eef2356d1c8ebd0e + uri: huggingface://bartowski/soob3123_GrayLine-Qwen3-8B-GGUF/soob3123_GrayLine-Qwen3-8B-Q4_K_M.gguf - &gemma3 url: "github:mudler/LocalAI/gallery/gemma.yaml@master" name: "gemma-3-27b-it" From f8fbfd4fa36d27b0267fb2414076f78e9ba12f84 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 19 May 2025 17:31:38 +0200 Subject: [PATCH 3/3] chore(model gallery): add a-m-team_am-thinking-v1 (#5395) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index d02288dc..2a8bb2c3 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -7282,6 +7282,30 @@ - filename: mmproj-Qwen_Qwen2.5-VL-72B-Instruct-f16.gguf sha256: 6099885b9c4056e24806b616401ff2730a7354335e6f2f0eaf2a45e89c8a457c uri: https://huggingface.co/bartowski/Qwen_Qwen2.5-VL-72B-Instruct-GGUF/resolve/main/mmproj-Qwen_Qwen2.5-VL-72B-Instruct-f16.gguf +- !!merge <<: *qwen25 + name: "a-m-team_am-thinking-v1" + icon: https://cdn-avatars.huggingface.co/v1/production/uploads/62da53284398e21bf7f0d539/y6wX4K-P9O8B9frsxxQ6W.jpeg + urls: + - https://huggingface.co/a-m-team/AM-Thinking-v1 + - https://huggingface.co/bartowski/a-m-team_AM-Thinking-v1-GGUF + description: | + AM-Thinking‑v1, a 32B dense language model focused on enhancing reasoning capabilities. Built on Qwen 2.5‑32B‑Base, AM-Thinking‑v1 shows strong performance on reasoning benchmarks, comparable to much larger MoE models like DeepSeek‑R1, Qwen3‑235B‑A22B, Seed1.5-Thinking, and larger dense model like Nemotron-Ultra-253B-v1. + benchmark + 🧩 Why Another 32B Reasoning Model Matters? + + Large Mixture‑of‑Experts (MoE) models such as DeepSeek‑R1 or Qwen3‑235B‑A22B dominate leaderboards—but they also demand clusters of high‑end GPUs. Many teams just need the best dense model that fits on a single card. AM‑Thinking‑v1 fills that gap while remaining fully based on open-source components: + + Outperforms DeepSeek‑R1 on AIME’24/’25 & LiveCodeBench and approaches Qwen3‑235B‑A22B despite being 1/7‑th the parameter count. + Built on the publicly available Qwen 2.5‑32B‑Base, as well as the RL training queries. + Shows that with a well‑designed post‑training pipeline ( SFT + dual‑stage RL ) you can squeeze flagship‑level reasoning out of a 32 B dense model. + Deploys on one A100‑80 GB with deterministic latency—no MoE routing overhead. + overrides: + parameters: + model: a-m-team_AM-Thinking-v1-Q4_K_M.gguf + files: + - filename: a-m-team_AM-Thinking-v1-Q4_K_M.gguf + sha256: a6da6e8d330d76167c04a54eeb550668b59b613ea53af22e3b4a0c6da271e38d + uri: huggingface://bartowski/a-m-team_AM-Thinking-v1-GGUF/a-m-team_AM-Thinking-v1-Q4_K_M.gguf - &llama31 url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1 icon: https://avatars.githubusercontent.com/u/153379578