πŸͺ™
Bible
  • πŸ“šbookshelf.crypto
  • πŸ“•Fundamentals
    • πŸͺ™Tokenomics
    • πŸͺ™Tokenomics tips
    • βš–οΈLiquidity Pools & Staking
    • πŸ“ˆNFTs in DEFI
    • βš™οΈUtility & example NFT collections
    • πŸ›οΈDAO & Governance
  • πŸ—οΈNitty gritty
    • πŸ’¬Lingo
    • πŸš—On & Off ramp
    • ❌xNFT
    • πŸͺ™Ethereum merge
    • ✍️bribing
    • πŸ‘›Cbdc & crypto
  • πŸ’­Wisdom
    • πŸ†•Creating a new product
    • πŸ’­Project Ideas
  • βš’οΈProtocols & utility
    • πŸͺ™$BLUR token
    • 🟒Shadow Drive
    • 🟒SPL-token Freezing
    • 🟒Cardinal
    • 🟒WOO X
    • 🟒Wormhole
    • 🟒Jump_
    • 🟒Saber
    • 🟒Solend
    • 🟒BTSE
    • πŸ”©Interesting utility
  • πŸ‘¨β€πŸ’ΌVCs
    • πŸ’°Venture Capital (VC Funds)
    • πŸ“”How VCs operate
    • 🏟️ESVCLP
    • πŸš—Sidecar
    • πŸ“„Trustees vs Beneficiaries
    • 🀝Mutual fund
    • 🐻Bare trust vs Unit trust
    • βš–οΈShareholders agreement
    • πŸ”Establishing a new VC
    • πŸ’°Tax incentives & benefits - WIP
    • πŸ“ Ben tax writeup
  • 🎯Marketing
    • πŸ“‘GTM - Go to market strategy - WIP
  • πŸ“˜Literature
    • 🏭Lean startup
    • πŸ“Founder’s Pocket Guide - Startup Valuation
    • πŸ˜„regret minimization framework
    • πŸ₯§Slicing pie
    • πŸ‘¨β€πŸ’ΌAgile vs. Lean
  • πŸ€–AI
    • GPT Best practices
    • Neural networks
    • Existing AI models
    • AI learning
    • LLMs
    • WASM AGI
    • πŸ’»Machine learning
  • 🧠Ideas
    • EarthID
    • HealthGuard
    • ⌚HealthGuard - product writeup
    • Sri Lanka ticketing platform
Powered by GitBook
On this page
  1. AI

Existing AI models

LLaMa

  • Built by Meta (Facebook) - collection of language models ranging from 7B to 65B parameters

  • LLaMA-13B is 10x more powerful then ChatGPT-3 while being 10x smaller

GPT

  • ChatGPT-3.5, ChatGPT-4 are examples of LLMs

  • ChatGPT has 175 billion parameters

llama.cpc

  • C/C++ model to quiery LLaMA model

  • Completely open source

  • Allows to run on the Mac

  • Only runs on the CPU

  • Lower accuracy & degradation - leads to lower precision (loss of information)

alpaca.cpp

  • Same as llama model

  • It is an instruction-follow model

  • Fine-tuned version of llama 7B

PreviousNeural networksNextAI learning

Last updated 2 years ago

πŸ€–