Compressing Large Language Models (LLMs) | w/ Python Code

Pubblicato il: 31 agosto 2024
sul canale di: Shaw Talebi

16,954

643

🤝 Want your team maximizing Claude? I run 1:1 and team AI workshops for companies doing $1M+ per year: https://aibuilder.academy/yt/FLkUOkeMd5M

Here, I discuss 3 ways to do model compression on LLMs (i.e. Quantization, Pruning, and Knowledge Distillation/Model Distillation) with example Python code.

Resources:
📰 Blog: https://medium.com/towards-data-scien...
🎥 Training the Teacher Model: • Fine-Tuning BERT for Text Classification (...

💻 GitHub Repo: https://github.com/ShawhinT/YouTube-B...
👩‍🏫 Teacher Model: https://huggingface.co/shawhin/bert-p...
🧑‍🎓 Student Model: https://huggingface.co/shawhin/bert-p...
👾 4-bit Student Model: https://huggingface.co/shawhin/bert-p...
💿 Dataset: https://huggingface.co/datasets/shawh...

References:
[1] https://arxiv.org/abs/2001.08361
[2] https://arxiv.org/abs/1710.09282
[3] https://machinelearning.apple.com/res...
[4] https://arxiv.org/abs/1710.09282
[5] https://arxiv.org/abs/2308.07633
[6] https://arxiv.org/abs/2402.17764
[7] https://arxiv.org/abs/1710.01878
[8] https://arxiv.org/abs/1503.02531
[9] https://crfm.stanford.edu/2023/03/13/...
[10] https://arxiv.org/abs/2305.14314
[11] https://www.researchgate.net/publicat...

Intro - 0:00
"Bigger is Better" - 0:40
The Problem - 1:35
Model Compression - 2:14
1) Quantization - 3:11
2) Pruning - 5:44
3) Knowledge Distillation - 8:04
Example: Compressing a model with KD + Quantization - 11:10

In questa pagina del sito puoi guardare il video online Compressing Large Language Models (LLMs) | w/ Python Code della durata di ore minuti seconda in buona qualità , che l'utente ha caricato Shaw Talebi 31 agosto 2024, condividi il link con amici e conoscenti, su youtube questo video è già stato visto 16,954 volte e gli è piaciuto 643 spettatori. Buona visione!