「直感LLM」1章まで進めた。
LLMってネット必須かと思ってたけど、ローカルでも動くのか…！
自分のMacでPhi-3 miniを実行してみたら、本当に動いた。
自分用に育てられたら、すごく便利になりそう。
これからの学びが楽しみ。

#直感LLM #AI学習 #Ollama #Phi3mini #ローカルLLM

Acknowledgements: Insights on vLLM Kernel from UC Berkeley

We extend gratitude to Zhuohan Li, Simon Mo, and Kaichao You from UC Berkeley for their valuable insights that contributed to the vLLM kernel discussion #phi3mini

The Research Team Behind the phi-3 LLM Development

Discover the names of the talented researchers and scientists who collaborated on the development and study of the phi-3 large language models. #phi3mini

Diverse Question Types in LLM Benchmark Prompts

Explore a sample prompt featuring varied multiple-choice questions covering math, science, and humanities #phi3mini

References on Responsible AI, Long-Context, and Data-Optimal LLMs

A compilation of cited works supporting our phi-3 research, including studies on responsible AI alignment, long-context models, data-optimal training strategies #phi3mini

Confronting Multimodal LLM Challenges: Reasoning Gaps and Safety Trade-offs in Phi-3-Vision

Explore the inherent challenges in Phi-3-Vision, from limitations in high-level reasoning and occasional ungrounded outputs to the complex trade-offs #phi3mini

Benchmarking Multimodal Safety: Phi-3-Vision's Robust RAI Performance

Explore Phi-3-Vision's robust safety evaluation on internal and public Multi-Modal RAI benchmarks (RTVLM, VLGuard) #phi3mini

Phi-3-Vision's Triumphant Performance on Key Multimodal Benchmarks

Witness Phi-3-Vision's impressive evaluation results across nine open-source academic benchmarks, challenging top multimodal LLMs like MM1, Llava, and Claude 3. #phi3mini

Unveiling phi-3-vision: Architecture, Pre-training, and Post-training for Visual AI

Explore the technical specifications of phi-3-vision, detailing its CLIP + phi-3-mini-128K architecture, and diverse multimodal pre-training dataset #phi3mini

Navigating LLM Frontiers: phi-3's Weaknesses and Augmentation Pathways

Explore the inherent challenges in even high-performing small LLMs like phi-3-mini, such as factual limitations and language restrictions #phi3mini

Fortifying LLM Safety: phi-3's Responsible AI Alignment

Discover how phi-3 models embody Microsoft’s responsible AI principles, featuring multi-stage safety alignment, rigorous red-teaming, and extensive evaluations #phi3mini

phi-3-mini's Triumph: Redefining Performance on Academic LLM Benchmarks

Witness phi-3-mini's impressive results on standard academic benchmarks for reasoning and logic, challenging models like Mistral 8x7B, Gemma 7B, and GPT-3.5 #phi3mini

Unpacking phi-3-mini: Architecture Driving Phone-Deployable LLM Power

Dive into phi-3-mini's technical core: a 3.8B Transformer decoder with 4K context (128K LongRope option), and a Llama-2-like block structure #phi3mini

phi-3-mini: The 3.8B Powerhouse Reshaping LLM Performance on Your Phone

Witness a breakthrough! phi-3-mini, a 3.8B parameter LLM, trained on 3.3T tokens, unleashes performance rivaling Mixtral 8x7B and GPT-3.5 #phi3mini

⚡ Big brains, small package.
Phi‑3‑mini brings GPT‑3.5 power to your phone, IoT, and beyond!

Follow Arbisoft for more smart AI in tiny spaces: https://f.mtr.cool/troskdkblc

#Phi3Mini #LLM #AIInnovation #Arbisoft #TechUpdates

⚡ Big brains, small package.
Phi‑3‑mini brings GPT‑3.5 power to your phone, IoT, and beyond!

Follow Arbisoft for more smart AI in tiny spaces: https://f.mtr.cool/troskdkblc

#Phi3Mini #LLM #AIInnovation #Arbisoft #TechUpdates

⚡ Big brains, small package.
Phi‑3‑mini brings GPT‑3.5 power to your phone, IoT, and beyond!

Follow Arbisoft for more smart AI in tiny spaces: https://f.mtr.cool/troskdkblc

#Phi3Mini #LLM #AIInnovation #Arbisoft #TechUpdates

LLM e smartphone: il futuro dell'IA mobile è qui La rivoluzione silenziosa degli smartphone: come i modelli IA LLM (large language models) stanno trasformando i nostri smartphone in assistenti IA personali

💡 LLM sugli smartphone: il futuro dell’IA nel palmo della tua mano

gomoot.com/llm-sugli-sm...

#ai #blog #gemini #gemma2b #ia #llm #nano #news #phi3mini #picks #smartphone #snapdragongen4 #tech #tecnologia

Apple-News rund um Mac, iPhone und iPad | MacTechNews.de Immer aktuelle Apple-News, Tipps, Tricks und Testberichte rund um Mac, iPhone, iPad und Co.

#KünstlicheIntelligenz fürs #iPhone: #Microsoft präsentiert #Phi3Mini als mobiles LLM | MacTechNews.de | Bin das skeptisch, wenn die mit KI generierten Inhalten trainiert ist, habe ich kein gesteigertes Vertrauen darin. 🤷‍♂️
www.mactechnews.de/news/article...

Getting Started - Generative AI with Phi-3-mini: A Guide to Inference and Deployment.

#ai #GenerativeAI #Phi3Mini #Phi3 #cloud #semantickernel #huggingface #onnx...

Introducing Phi-3: Redefining what's possible with SLMs |... We are excited to introduce Phi-3, a family of small open...

Introducing Phi-3: Redefining what’s possible with SLMs.

#ai #Phi3 #Phi3Mini #SLM #microsoft #cloud #azure #aimodels
azure.microsoft.com/en-us/blog/introducing-p...

Getting Started - Generative AI with Phi-3-mini: A Guide to Inference and Deployment Discover how Phi-3-mini, a new series of models from Microsoft, enables deployment of Large Language Models (LLMs) on edge devices and IoT devices. Learn how to use Semantic Kernel, Ollama/LlamaEdge, ...

Getting Started - Generative AI with Phi-3-mini: A Guide to Inference and Deployment.

#ai #GenerativeAI #Phi3Mini #Phi3 #cloud #semantickernel #huggingface #onnx
techcommunity.microsoft.com/t5/microsoft...

Phi-3-Mini, nuovo modello LLM compatto di Microsoft Microsoft lancia Phi-3-Mini, un modello di intelligenza artificiale compatto ideale per smartphone e laptop o dispositivi con risorse limitate

👉 Microsoft lancia il modello LLM Phi-3-Mini
Microsoft lancia Phi-3-Mini, un modello IA compatto ideale per smartphone e laptop o dispositivi con risorse limitate

gomoot.com/microsoft-la...

#AI #blog #ia #LLM #Microsoft #mistral #Mixtral #news #phi3medium #phi3mini #phi3small #tech #tecnologia