top | item 40979667 (no title) osanseviero | 1 year ago Hi all! I'm Omar from Hugging Face. Happy to answer any questions you might have about Hugging Face in general, llamas, and open ML! discuss order hn newest brianjking|1 year ago I'd love to work at Hugging Face! Happen to be hiring any new dev relations/product/AI engineer type roles?This is such a great piece. ZoomerCretin|1 year ago Could you talk more about HuggingFace's new benchmark for LLMs? When did it become obvious that the old benchmarks were no longer sufficient: swyx|1 year ago [author here] we interviewed the maintainer of that leaderboard if you want to hear from her directly! https://www.latent.space/p/benchmarks-201tldr: old benchmarks saturated, methodology was liable to a lot of subtle biases. as she mentions on the pod, they're already working on leaderboard v3. Hooray_Darakian|1 year ago How large is the staff at hugging face? abidlabs|1 year ago We have ~220 total team members across all roles
brianjking|1 year ago I'd love to work at Hugging Face! Happen to be hiring any new dev relations/product/AI engineer type roles?This is such a great piece.
ZoomerCretin|1 year ago Could you talk more about HuggingFace's new benchmark for LLMs? When did it become obvious that the old benchmarks were no longer sufficient: swyx|1 year ago [author here] we interviewed the maintainer of that leaderboard if you want to hear from her directly! https://www.latent.space/p/benchmarks-201tldr: old benchmarks saturated, methodology was liable to a lot of subtle biases. as she mentions on the pod, they're already working on leaderboard v3.
swyx|1 year ago [author here] we interviewed the maintainer of that leaderboard if you want to hear from her directly! https://www.latent.space/p/benchmarks-201tldr: old benchmarks saturated, methodology was liable to a lot of subtle biases. as she mentions on the pod, they're already working on leaderboard v3.
Hooray_Darakian|1 year ago How large is the staff at hugging face? abidlabs|1 year ago We have ~220 total team members across all roles
brianjking|1 year ago
This is such a great piece.
ZoomerCretin|1 year ago
swyx|1 year ago
tldr: old benchmarks saturated, methodology was liable to a lot of subtle biases. as she mentions on the pod, they're already working on leaderboard v3.
Hooray_Darakian|1 year ago
abidlabs|1 year ago