Thanks! I added the check marks because when I was testing different quantizations, I often picked a model and only afterwards discovered that it couldn’t even load — it just didn’t fit into RAM or VRAM.
So the check mark simply indicates that the model can actually run under those constraints (fits in memory), not that it’s selected.
[…]the model’s internal representations become more aligned with human neural activity after fine-tuning. Taken together, our results demonstrate that it is possible to discover computational models that capture human behaviour across a wide range of domains.
Hi Eric, my name is Francesco. In the last three years we industrialized a novel method for producing biosimilar insulin (in Italy). We are an international team and I really would like to contact you. Can you write to the email you find on my profile?
So the check mark simply indicates that the model can actually run under those constraints (fits in memory), not that it’s selected.