Yann LeCun
@ylecun · Apr 18, 2024
🥁 Llama3 is out 🥁
8B and 70B models available today.
8k context length.
Trained with 15 trillion tokens on a custom-built 24k GPU cluster.
Great performance on various benchmarks, with Llam3-8B doing better than Llama2-70B in some cases.
More versions are coming over the next
Elon Musk
@elonmusk
Not bad
04:42 PM · April 18, 2024 · 96.9K views
67
37
1.4K