makiisthebes/gemma-2-2b-Instruct-NL2SQL
Updated
•
73
•
1
Michael Peres
makiisthebes
AI & ML interests
TinyML | Transformers | Reinforcement Learning | Learning through practice, MSc AI Student
Recent Activity
liked
a model
10 days ago
makiisthebes/gemma-2-2b-Instruct-NL2SQL
updated
a model
10 days ago
makiisthebes/gemma-2-9b-Instruct-NL2SQL
updated
a model
10 days ago
makiisthebes/gemma-2-2b-Instruct-NL2SQL
Organizations
None yet
makiisthebes's activity
liked
a
model
10 days ago
updated
2
models
10 days ago
liked
a
dataset
10 days ago
liked
a
dataset
11 days ago
liked
a
model
23 days ago
liked
a
dataset
26 days ago
liked
a
model
26 days ago
liked
a
dataset
26 days ago
updated
a
dataset
3 months ago
I am sure more work on inference will be done, looks pretty exciting, possibly reducing the model sizes quite a bunch!
reacted to
Sentdex's
post with 🔥
7 months ago
Post
8414
Okay, first pass over KAN: Kolmogorov–Arnold Networks, it looks very interesting!
Interpretability of KAN model:
May be considered mostly as a safety issue these days, but it can also be used as a form of interaction between the user and a model, as this paper argues and I think they make a valid point here. With MLP, we only interact with the outputs, but KAN is an entirely different paradigm and I find it compelling.
Scalability:
KAN shows better parameter efficiency than MLP. This likely translates also to needing less data. We're already at the point with the frontier LLMs where all the data available from the internet is used + more is made synthetically...so we kind of need something better.
Continual learning:
KAN can handle new input information w/o catastrophic forgetting, which helps to keep a model up to date without relying on some database or retraining.
Sequential data:
This is probably what most people are curious about right now, and KANs are not shown to work with sequential data yet and it's unclear what the best approach might be to make it work well both in training and regarding the interpretability aspect. That said, there's a rich long history of achieving sequential data in variety of ways, so I don't think getting the ball rolling here would be too challenging.
Mostly, I just love a new paradigm and I want to see more!
KAN: Kolmogorov-Arnold Networks (2404.19756)
Interpretability of KAN model:
May be considered mostly as a safety issue these days, but it can also be used as a form of interaction between the user and a model, as this paper argues and I think they make a valid point here. With MLP, we only interact with the outputs, but KAN is an entirely different paradigm and I find it compelling.
Scalability:
KAN shows better parameter efficiency than MLP. This likely translates also to needing less data. We're already at the point with the frontier LLMs where all the data available from the internet is used + more is made synthetically...so we kind of need something better.
Continual learning:
KAN can handle new input information w/o catastrophic forgetting, which helps to keep a model up to date without relying on some database or retraining.
Sequential data:
This is probably what most people are curious about right now, and KANs are not shown to work with sequential data yet and it's unclear what the best approach might be to make it work well both in training and regarding the interpretability aspect. That said, there's a rich long history of achieving sequential data in variety of ways, so I don't think getting the ball rolling here would be too challenging.
Mostly, I just love a new paradigm and I want to see more!
KAN: Kolmogorov-Arnold Networks (2404.19756)
- 5 replies
updated
a
model
7 months ago
updated
a
model
9 months ago
liked
a
model
9 months ago
updated
a
model
9 months ago
liked
a
model
9 months ago
updated
a
model
9 months ago
liked
a
model
10 months ago
updated
a
model
10 months ago