Futures
Access hundreds of perpetual contracts
TradFi
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Pre-IPOs
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
pmarca shares information about a 3.3 billion-parameter model trained on historical text
ME News Report, April 3rd (UTC+8), recently, well-known figure pmarca shared information about model pretraining on social media. According to his post, the model’s pretraining corpus used American and British books and newspapers from before January 1, 1900, sourced from Huggingface and Internet Archive. After extensive filtering, approximately 22B tokens were compiled into the training dataset. The article mentions that the best checkpoint of this model is a 3.3 billion parameter model. pmarca stated that he has been looking forward to such developments since December 1, 2022. (Source: InFoQ)