#fsldeeplearning search results

Fine-tune DeepSeek OCR locally! DeepSeek dropped a new OCR model built for document understanding and long-context reasoning. It’s a 3B parameter vision model that uses context optical compression to convert 2D document layouts into compact vision tokens instead of thousands of…

LLMs (Large Language Models) Learning Roadmap |-- Foundations of Machine Learning | |-- Linear Algebra, Probability & Statistics | |-- Supervised, Unsupervised & Reinforcement Learning | |-- Model Training, Validation & Evaluation | |-- Overfitting, Regularization &…

Diffusion Language Models are Super Data Learners "when unique data is limited, diffusion language models (DLMs) consistently surpass autoregressive (AR) models by training for more epochs." "At scale, a 1.7B DLM trained with a ∼ 1.5T - token compute budget on 10B unique…

1/ Today, we’re thrilled to announce that @Felicis has led the Series A investment in @DeepJudgeAI, which we believe is building the future of legal tech.

How can you transform a traditional meeting into an impactful Active Deep Learner eXperience? 🚪 segagroup.net/mr-abdulrahman… #Inspiring_Impact #Learner_eXperience #active_deep_learner_experience #FIRST_ADLX_Framework

You can now fine-tune DeepSeek-OCR with our free notebook! We fine-tuned DeepSeek-OCR, improving its language understanding by 89%, and reduced Character Error Rate from 149% to 60% Blog: docs.unsloth.ai/new/deepseek-o… GitHub: github.com/unslothai/unsl… Colab: colab.research.google.com/github/unsloth…

🚀 Introducing Expert-Specialized Fine-Tuning (ESFT) for Customizing LLMs with Sparse Architectures! 🌟 Highlights: - Train only task-relevant experts for LLM customization. - Reduces storage by up to 90% and training time by up to 30%. ✨ Performance: - Customizes LLMs…

Qullamaggie Setups to Study: $FSLY Aug 20 2020 "Someone wrote to me in the chat like what do you see - why do you see it as a long They couldn't get it - like why is this a long Its very easy. It's a momentum leader. Made a big move, like this thing went up 1000% ina few…

Federated Learning is an ML domain that will get a huge boost in upcoming years but at the same time might saturate quickly. Let's breakdown this in very simple terms ( I haven't completed FL yet but sharing of what i know and understood up till now ) - > You might have heard…

Always racing to keep up with new LLMs? DeepSeek models make it easier. Learn to build one from scratch and cut the friction that slows you down with Build a DeepSeek Model (From Scratch). Now in MEAP — 50% off for the next couple of weeks: hubs.la/Q03RT-dF0

If you want to explore FL more you can check out these free to learn courses - > Intro to Federated Learning on Deep Learning > Federated Fine-tuning of LLMs with Private Data on Deep Learning > CS -E470 by Alexander Jung on yt !

#DeepAnalyze-8B — an open-source agentic LLM for autonomous data science The model performs the entire data-science pipeline — from raw data to analyst-grade research reports — without predefined workflows. It’s trained through a curriculum-based agentic learning paradigm and…

Absolutely love this Stanford Deep Learning for Computer Vision taught by Professor Fei-Fei Li (@drfeifei ) and Assistant Professor Ehsan Adeli. 👌 Such an enjoyable YT series. (link in comment)

It’s time! After our successful Beta program with over 1,000 early adopters, DeepL Agent is now generally available and ready to start transforming how work gets done for your organization. Our Chief Scientist Stefan Mesken took to the stage at DeepL Dialogues to announce the…

Being part of @inference_labs’ Zealy campaign has been eye-opening. It’s not just about earning rewards — it’s about understanding how decentralized inference can redefine AI’s future.

Stanford CS224N NLP with deep learning your knowledge of LLMs is nothing without an NLP foundation

Tom Lee (@fundstrat) and Jansen Teng (@virtuals_io) explore AI agents, crypto-powered infrastructure, and the potential opportunities at their intersection. Plus, a quick look at Tom’s crypto outlook heading into Q4’25👀 🎥 Watch the full (free) session: fsinsight.com/event/the-agen……

Continuing our IMO-gold journey, I’m delighted to share our #EMNLP2025 paper “Towards Robust Mathematical Reasoning”, which tells some of the key stories behind the success of our advanced Gemini #DeepThink at this year IMO. Finding the right north-star metrics was highly…

Finally done with DL 🚀🔊, ended the Deep Learning journey with bidirectional RNNs During all these days i was not posting regularly due to office excessive workload but i just made sure not to stop the daily lectures. After all this, i’m finally going to start the thing due…