Ne sentivamo tutti il bisogno#lora #meshtastic #ai #ia #porcamadonna
Ne sentivamo tutti il bisogno#lora #meshtastic #ai #ia #porcamadonna
#Fine-Tuning
322 articles tagged with Fine-Tuning
Fine-Tune, Evaluate, Publish: Release a LoRA Adapter With GatesThe last step of a fine-tune is not "push". Pick a licens...
Fine-Tune, Evaluate, Publish: Release a LoRA Adapter With GatesThe last step of a fine-tune is not "push". Pick a licensed base, split your data, train a LoRA adapter, compare it w...
🚀 نبض الأسواق الرقمية:UGREEN USB C to Ethernet Adapter, 4 in 1 USB C Hub Ethernet with 3 USB 3.0 Ports/Gigabit Rj45, Plu...
🚀 نبض الأسواق الرقمية:UGREEN USB C to Ethernet Adapter, 4 in 1 USB C Hub Ethernet with 3 USB 3.0 Ports/Gigabit Rj45, Plug & Play, Thunderbolt (3/4) to Network Adapter for MacBook P...
🚀 نبض الأسواق الرقمية:4 Port USB 3.0 Hub, 5 Gbps Data Multi Port Expander Extender Lead Adapter for Laptop, Flash Drives...
🚀 نبض الأسواق الرقمية:4 Port USB 3.0 Hub, 5 Gbps Data Multi Port Expander Extender Lead Adapter for Laptop, Flash Drives, Mobile HDD, and More, Compatible With USB Port Devicesاكتش...
🚀 نبض الأسواق الرقمية:USB Hub Adapter DS-44U, 4-Port Type-A Splitter with Attached Cable, Slim Metallic Grey Expander fo...
🚀 نبض الأسواق الرقمية:USB Hub Adapter DS-44U, 4-Port Type-A Splitter with Attached Cable, Slim Metallic Grey Expander for Peripheral Connectionsاكتشف كيف توفر وكالة مراد الوقت واله...
🚀 نبض الأسواق الرقمية:Dioche USB-C Hub, 5-in-1 USB-C Adapter with 4K HDMI, HD-PD High Speed Transmission Multi-Function ...
🚀 نبض الأسواق الرقمية:Dioche USB-C Hub, 5-in-1 USB-C Adapter with 4K HDMI, HD-PD High Speed Transmission Multi-Function Converter Adapterاكتشف كيف توفر وكالة مراد الوقت والهدر التش...
Text-to-SQL em português com RAG e LoRA: o que aprendi medindo um assistente sobre dados sintéticos
Montei um assistente que transforma perguntas em português sobre uma frota de ônibus em SQL, e passei...
📰 Latent — A 27B model de-propagandised, plus a vLLM control plane• Nous Research releases Arete-27B, a Qwen3.8 fine-tun...
📰 Latent — A 27B model de-propagandised, plus a vLLM control plane• Nous Research releases Arete-27B, a Qwen3.8 fine-tune that nearly eliminates propaganda answers• Buoyant open-so...
Препарируем мозг Qwen 3.8 27B-1cЕсть Qwen 3.8 27B, дообученная (SFT + LoRA) на корпусе по платформе 1С:Предприятие — мод...
Препарируем мозг Qwen 3.8 27B-1cЕсть Qwen 3.8 27B, дообученная (SFT + LoRA) на корпусе по платформе 1С:Предприятие — модель выложена на hugging face. Модель неплохо пишет код на вс...
How I built one shared core for Telegram, Discord and Slack: a manifest, an adapter, and no fourth copy
Ankita AI is a desktop AI assistant by Krish Verma, and until last week it talked to Telegram in two...
A study shows that the training-data domain of LoRA-fine-tuned language models can be identified from model artifacts.So...
A study shows that the training-data domain of LoRA-fine-tuned language models can be identified from model artifacts.Source: arXivhttps://arxiv.org/abs/2611.07610#MachineLearning
Show HN: Interactive notes on RLHF, attention, LoRA and LLM evalshttps://concepts.laxmena.com/#llm
Show HN: Interactive notes on RLHF, attention, LoRA and LLM evalshttps://concepts.laxmena.com/#llm
ProLand is a retraction-free optimizer that separates objective optimization from orthogonality restoration for LoRA fin...
ProLand is a retraction-free optimizer that separates objective optimization from orthogonality restoration for LoRA fine-tuning.Source: arXiv cs.LGhttps://arxiv.org/abs/2611.00236...
MindrLabs/image-generation-qwen-image-pruna: Turn a text prompt into a 1024×1024 image in 6 steps, locally with Qwen-Image-2.1, the P-Q-Image-2.1 LoRA and model-compose.
Turn a text prompt into a 1024×1024 image in 6 steps, locally with Qwen-Image-2.1, the P-Q-Image-2.1 LoRA and model-compose.
Samaya AI has released Sterling, a post-trained LoRA variant of NVIDIA Nemotron 3.5 Lightning tuned for agentic financia...
Samaya AI has released Sterling, a post-trained LoRA variant of NVIDIA Nemotron 3.5 Lightning tuned for agentic financial research. It scores 58.9% on the FrontierFinance benchmark...
ファインチューニングとLoRAを実践で使いこなす完全ガイド【事例・比較・学習リソース】ファインチューニングと軽量適応（LoRA）の基礎から実装手順、Databricksをはじめとした実際の活用事例、主要ツール比較表、関連書籍リンクまで網羅し...
ファインチューニングとLoRAを実践で使いこなす完全ガイド【事例・比較・学習リソース】ファインチューニングと軽量適応（LoRA）の基礎から実装手順、Databricksをはじめとした実際の活用事例、主要ツール比較表、関連書籍リンクまで網羅した2000文字超の実践ガイドです。https://ai-blog-seven-wine.vercel.app/ja/po...
umaircxnd/MiniMax-H3-Turbo-Lora-UNCENSORED-Workflow - AI Space/Demo
Hugging Face Space: umaircxnd/MiniMax-H3-Turbo-Lora-UNCENSORED-Workflow
🚀 Fastest-growing AI projects today1. From multimodal training systems to specialized LoRA fine-tuning tools, the commun...
🚀 Fastest-growing AI projects today1. From multimodal training systems to specialized LoRA fine-tuning tools, the community c...2. Valen-Team/Valen leads the pack thweek with a sig...
Infini-AI-Lab has open-sourced Hermit, a harness adapter framework that trains an external module for AI agents while th...
Infini-AI-Lab has open-sourced Hermit, a harness adapter framework that trains an external module for AI agents while the agent's model and harness stay frozen. It lets Codex or Cl...
📰 Infini-AI-Lab Releases Hermit, an Open-Source Harness Adapter Framework for AI AgentsInfini-AI-Lab released Hermit, an...
📰 Infini-AI-Lab Releases Hermit, an Open-Source Harness Adapter Framework for AI AgentsInfini-AI-Lab released Hermit, an Apache-2.0 harness adapter framework that trains an externa...
ElectronGirl/sd-forge-anima-ref-adapter: Anima Reference Adapter v2 for Stable Diffusion WebUI Forge Neo: character and style from a reference image
Anima Reference Adapter v2 for Stable Diffusion WebUI Forge Neo: character and style from a reference image
eduardoabreu81/anima-reference-forge-neo: Anima character reference for Stable Diffusion WebUI Forge Neo: one picture of a character, any scene from the prompt, with ElectronGirl's Ref Adapter and AnticPan's Role Ref KV
Anima character reference for Stable Diffusion WebUI Forge Neo: one picture of a character, any scene from the prompt, with ElectronGirl's Ref Adapter and AnticPan's Role Ref KV
M6来ましたですApple Releases Redesigned Mac Chargers and 'World Travel Adapter Kit' https://www.macrumors.com/2026/10/28/apple...
M6来ましたですApple Releases Redesigned Mac Chargers and 'World Travel Adapter Kit' https://www.macrumors.com/2026/10/28/apple-new-world-travel-adapter-kit/#Apple #LLM #news #bot
LoRA on a 16 GB card: what fits and what does not
A 7B model is the honest ceiling for LoRA fine-tuning on a 16 GB consumer card, not because anything...