Large Language Models
Neural networks trained on internet-scale text to predict the next word — and which, at sufficient scale, turn out to translate, code, reason, and converse without being taught any of those skills directly.
गहरा अभिलेखागार फ़िलहाल अंग्रेज़ी में लिखा है — सत्यापित अनुवाद रोडमैप का हिस्सा हैं। आपके ब्राउज़र की अनुवाद सुविधा इस पृष्ठ पर अच्छी तरह काम करती है।
✦ अरे, सच में?
An LLM's entire education is a single game: guess the next word. Nobody programmed translation, arithmetic, or coding into them — those abilities emerged, uninvited, once the models and their training data got big enough — though just how sharply they emerge is contested.
यह क्या है
A transformer neural network with hundreds of billions of parameters — GPT-3 had 175 billion, with frontier models estimated to reach the trillions — trained to predict the next token across trillions of words of text, then refined with human feedback into a conversational assistant.
यह क्यों महत्वपूर्ण था
Language is the interface to almost all recorded human knowledge. A machine that genuinely handles language becomes a general-purpose collaborator — the first technology in this graph that can read the graph itself.
यह कैसे बनाया गया
Web-scale text is tokenized and fed through a transformer trained by gradient descent on next-token prediction, typically across thousands of GPUs for months; a second, far smaller phase aligns the raw predictor into a helpful assistant via human preference feedback.
इसने क्या संभव किया
Open — this is currently a frontier node of the graph. Candidate downstream nodes: AI-assisted software engineering, machine-readable knowledge corpora (this project), autonomous agents and robotics.
न्यूनतम कार्यक्षम संस्करण
A transformer-architecture network (2017) trained autoregressively on a large web-text corpus — the GPT recipe.
इसके लिए चाहिए
इससे खुला
सीमांत — आगे अभी कुछ अंकित नहीं।
इस क्षमता से गुज़रने वाले सूत्र
How did lightning become ChatGPT?12 क़दमस्रोत
- — Vaswani et al., 'Attention Is All You Need' (2017)
- — Brown et al., 'Language Models are Few-Shot Learners' (2020)
इस पृष्ठ पर कुछ ग़लत दिखा? यहाँ का हर दावा चुनौती झेलने के लिए लिखा गया है। सुधार सुझाइए →