Linying Lv

Visiting Finance PhD student at Washington University in St Louis

[Linying Lv @LinyingLyu]

👉 Public models and datasets available at: https://t.co/qwJTOBoya9

#AI #Finance #LLM #ChronoGPT #OpenSource #GenerativeAI

[Linying Lv @LinyingLyu]

🚀 Introducing ChronoGPT-instruct
Excited to share the latest instruction-tuned ChronoGPTs, joint work with @hesongrun, @AsafManela, and @JimmyCMWu . A series of high-performance, chronologically consistent, instruction-following LLMs designed to eliminate lookahead bias.

[Linying Lv @LinyingLyu]

📄 The accompanying paper, Chronologically Consistent Generative AI (https://t.co/7Cmas5XfcN), details our methodology and validation.

[Linying Lv @LinyingLyu]

⏳Happy to share our ChronoBERT series!

[Songrun He @hesongrun]

🚀 Introducing ChronoBERT: A Chronologically Consistent Language Model ⏳📜

Excited to share ChronoBERT, a joint work with @LinyingLyu , @AsafManela , and @jimmywucm ! Our new pre-trained language model ensures no lookahead bias and strong language understanding! 🧠✨

[Andrej Karpathy @karpathy]

nanoGPT speedrun: Nice work from @kellerjordan0 adapting the nanoGPT/llmc PyTorch training code into a benchmark training a 124M Transformer to a fixed validation loss target. Current SOTA is 3.8X more token-efficient training (2.7B vs. 10B tokens)