From 2dcb6d72475ae3cdf073ebab7d08bee13eb517ae Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Sat, 10 May 2025 22:24:04 +0200 Subject: [PATCH] chore(model-gallery): :arrow_up: update checksum (#5346) :arrow_up: Checksum updates in gallery/index.yaml Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --- gallery/index.yaml | 38 ++++++++++++++++---------------------- 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index 8125af12..f35f3c46 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -584,24 +584,24 @@ - https://huggingface.co/Daemontatox/Qwen3-14B-Griffon - https://huggingface.co/mradermacher/Qwen3-14B-Griffon-i1-GGUF description: | - This is a fine-tuned version of the Qwen3-14B model using the high-quality OpenThoughts2-1M dataset. Fine-tuned with Unsloth’s TRL-compatible framework and LoRA for efficient performance, this model is optimized for advanced reasoning tasks, especially in math, logic puzzles, code generation, and step-by-step problem solving. - Training Dataset + This is a fine-tuned version of the Qwen3-14B model using the high-quality OpenThoughts2-1M dataset. Fine-tuned with Unsloth’s TRL-compatible framework and LoRA for efficient performance, this model is optimized for advanced reasoning tasks, especially in math, logic puzzles, code generation, and step-by-step problem solving. + Training Dataset - Dataset: OpenThoughts2-1M - Source: A synthetic dataset curated and expanded by the OpenThoughts team - Volume: ~1.1M high-quality examples - Content Type: Multi-turn reasoning, math proofs, algorithmic code generation, logical deduction, and structured conversations - Tools Used: Curator Viewer + Dataset: OpenThoughts2-1M + Source: A synthetic dataset curated and expanded by the OpenThoughts team + Volume: ~1.1M high-quality examples + Content Type: Multi-turn reasoning, math proofs, algorithmic code generation, logical deduction, and structured conversations + Tools Used: Curator Viewer - This dataset builds upon OpenThoughts-114k and integrates strong reasoning-centric data sources like OpenR1-Math and KodCode. - Intended Use + This dataset builds upon OpenThoughts-114k and integrates strong reasoning-centric data sources like OpenR1-Math and KodCode. + Intended Use - This model is particularly suited for: + This model is particularly suited for: - Chain-of-thought and step-by-step reasoning - Code generation with logical structure - Educational tools for math and programming - AI agents requiring multi-turn problem-solving + Chain-of-thought and step-by-step reasoning + Code generation with logical structure + Educational tools for math and programming + AI agents requiring multi-turn problem-solving overrides: parameters: model: Qwen3-14B-Griffon.i1-Q4_K_M.gguf @@ -7078,13 +7078,7 @@ urls: - https://huggingface.co/ServiceNow-AI/Apriel-Nemotron-15b-Thinker - https://huggingface.co/bartowski/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF - description: | - Apriel-Nemotron-15b-Thinker is a 15 billion‑parameter reasoning model in ServiceNow’s Apriel SLM series which achieves competitive performance against similarly sized state-of-the-art models like o1‑mini, QWQ‑32b, and EXAONE‑Deep‑32b, all while maintaining only half the memory footprint of those alternatives. It builds upon the Apriel‑15b‑base checkpoint through a three‑stage training pipeline (CPT, SFT and GRPO). - Highlights - Half the size of SOTA models like QWQ-32b and EXAONE-32b and hence memory efficient. - It consumes 40% less tokens compared to QWQ-32b, making it super efficient in production. 🚀🚀🚀 - On par or outperforms on tasks like - MBPP, BFCL, Enterprise RAG, MT Bench, MixEval, IFEval and Multi-Challenge making it great for Agentic / Enterprise tasks. - Competitive performance on academic benchmarks like AIME-24 AIME-25, AMC-23, MATH-500 and GPQA considering model size. + description: "Apriel-Nemotron-15b-Thinker is a 15 billion‑parameter reasoning model in ServiceNow’s Apriel SLM series which achieves competitive performance against similarly sized state-of-the-art models like o1‑mini, QWQ‑32b, and EXAONE‑Deep‑32b, all while maintaining only half the memory footprint of those alternatives. It builds upon the Apriel‑15b‑base checkpoint through a three‑stage training pipeline (CPT, SFT and GRPO).\nHighlights\n Half the size of SOTA models like QWQ-32b and EXAONE-32b and hence memory efficient.\n It consumes 40% less tokens compared to QWQ-32b, making it super efficient in production. \U0001F680\U0001F680\U0001F680\n On par or outperforms on tasks like - MBPP, BFCL, Enterprise RAG, MT Bench, MixEval, IFEval and Multi-Challenge making it great for Agentic / Enterprise tasks.\n Competitive performance on academic benchmarks like AIME-24 AIME-25, AMC-23, MATH-500 and GPQA considering model size.\n" overrides: parameters: model: ServiceNow-AI_Apriel-Nemotron-15b-Thinker-Q4_K_M.gguf @@ -9013,8 +9007,8 @@ model: deepseek-r1-distill-llama-8b-Q4_K_M.gguf files: - filename: deepseek-r1-distill-llama-8b-Q4_K_M.gguf - sha256: f8eba201522ab44b79bc54166126bfaf836111ff4cbf2d13c59c3b57da10573b uri: huggingface://unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf + sha256: 0addb1339a82385bcd973186cd80d18dcc71885d45eabd899781a118d03827d9 - !!merge <<: *llama31 name: "selene-1-mini-llama-3.1-8b" icon: https://atla-ai.notion.site/image/https%3A%2F%2Fprod-files-secure.s3.us-west-2.amazonaws.com%2Ff08e6e70-73af-4363-9621-90e906b92ebc%2F1bfb4316-1ce6-40a0-800c-253739cfcdeb%2Fatla_white3x.svg?table=block&id=17c309d1-7745-80f9-8f60-e755409acd8d&spaceId=f08e6e70-73af-4363-9621-90e906b92ebc&userId=&cache=v2