this post was submitted on 24 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
How to replicate "Temporal perception" benchmark tests from the official paper for LLama2? (alien.top)
submitted 11 months ago by Hyzhak@alien.top to c/localllama@poweruser.forum
1 comments fedilink hide all child comments
 

Hi all,

The official paper (http://arxiv.org/abs/2307.09288) mentions "LLama 2-Chat temporal Perception" abilities (p33) and figure 22 illustrates "Time awareness" of the model.

But how did they provide yearly context to the model?

I'd like to replicate a similar benchmark for Llama2 and other LLMs but it isn't clear how to replicate the same setup.

you are viewing a single comment's thread
view the rest of the comments
[–] Mescallan@alien.top 1 points 11 months ago

Commenting to follow, this is fascinating.