lpasselin · HackerTrans

anno scorsodiscuss

A lawyer can become a locksmith in a few months (weeks? days?). If the flip mentioned is really happening, isn't it temporary?

lpasselin

anno scorsodiscuss

Hey, I read the paper in detail and presented to colleagues during our reading group.

I still do not understand exactly where D1L comes from in LGan(D1L, T(A1(u)). Is D1L simply A1(u)?

I also find that mixing notation in figure 2 and 3 makes it tricky.

Would have loved to have more insights from the results in the tables.

And more results from inversion, on more than Enron dataset. Since that is one end goals, even if reusing another method.

Thank you for the paper, very interesting!

lpasselin

2 anni fadiscuss

Do the captured elements move a lot during this snapshot? since it will take months? Is the difference significant?

lpasselin

2 anni fadiscuss

This comes from the same group as the EfficientViT model. A few months ago, their EfficientViT model was the only modern and small ViT style model I could find that had raw pytorch code available. No dependencies to the shitty framework and libraries that other ViT are using.

lpasselin

2 anni fadiscuss

Custom and _competent_ AI tutors will be a game changer for education.

lpasselin

2 anni fadiscuss

Meanwhile, I had a hard time last week getting a machine with 8 gpus from azure.

lpasselin

2 anni fadiscuss

I have a 200$ mini machine and would like to upgrade. Can DIY anything. What would you suggest for a maximum budget of 1500$?

lpasselin

2 anni fadiscuss

The mamba paper shows significant improvements in all model sizes, up to 1b, the largest one tested.

Are there any reason why it wouldn't scale to 7b or more? Have they tried it?

lpasselin

2 anni fadiscuss

Most of the leaderboard has much lower sequence length.

lpasselin

3 anni fadiscuss

Last time I tried, it did not have a good android app working.

lpasselin

3 anni fadiscuss

What are these websites??

lpasselin

3 anni fadiscuss

I actually tried this last year, before OpenAI released their cheaper embeddings v2 in december. From my experiments, when compared to Bert embeddings (or recent variation of the model) the OpenAI embeddings are miles ahead when doing similarity search.

comments