answerdotai/ModernBERT-large
Fill-Mask
β’
Updated
β’
23.8k
β’
284
Umar Butler
umarbutler
AI & ML interests
Law, technology, AI and everything in between.
Recent Activity
liked
a model
14 days ago
answerdotai/ModernBERT-large
new activity
14 days ago
answerdotai/ModernBERT-base:Is this model meant for full bfloat16, AMP bfloat16 or no bfloat16?
Organizations
umarbutler's activity
liked
a
model
14 days ago
Is this model meant for full bfloat16, AMP bfloat16 or no bfloat16?
#7 opened 14 days ago
by
umarbutler
liked
a
model
14 days ago
semantic search for models, datasets, etc... would be awesome and is critically lacking! (eg, if you wanted to find all the legal datasets on Hugging Face, you're better off using Google. "law", "contract", "legal", etc.. you'd need to search them all and then you have stuff like umarbutler/emubert which doesn't mention law in its title but is definitely legal related).
liked
a
dataset
2 months ago
Why not SNLI?
1
#6 opened 2 months ago
by
umarbutler
liked
a
dataset
3 months ago
Premise and hypothesis wrong way around?
2
#2 opened 10 months ago
by
MoritzLaurer
liked
2
datasets
3 months ago
liked
a
Space
3 months ago
Significant train/test imbalance makes this more tailored to GenAI rather than LLMs in general
3
#31 opened 3 months ago
by
umarbutler
liked
a
model
3 months ago
reacted to
MoritzLaurer's
post with π
3 months ago
Post
1627
Why would you fine-tune a model if you can just prompt an LLM? The new paper "What is the Role of Small Models in the LLM Era: A Survey" provides a nice pro/con overview. My go-to approach combines both:
1. Start testing an idea by prompting an LLM/VLM behind an API. It's fast and easy and I avoid wasting time on tuning a model on a task that might not make it into production anyways.
2. The LLM/VLM then needs to be manually validated. Anyone seriously considering putting AI into production has to do at least some manual validation. Setting up a good validation pipeline with a tool like Argilla is crucial and it can be reused for any future experiments. Note: you can use LLM-as-a-judge to automate some evals, but you always also need to validate the judge!
3. Based on this validation I can then (a) either just continue using the prompted LLM if it is accurate enough and it makes sense financially given my load; or (b) if the LLM is not accurate enough or too expensive to run in the long-run, I reuse the existing validation pipeline to annotate some additional data for fine-tuning a smaller model. This can be sped up by reusing & correcting synthetic data from the LLM (or just pure distillation).
Paper: https://arxiv.org/pdf/2409.06857
Argilla docs: https://docs.argilla.io/latest/
Argilla is also very easy to deploy with Hugging Face Spaces (or locally): https://huggingface.co/new-space?template=argilla%2Fargilla-template-space
1. Start testing an idea by prompting an LLM/VLM behind an API. It's fast and easy and I avoid wasting time on tuning a model on a task that might not make it into production anyways.
2. The LLM/VLM then needs to be manually validated. Anyone seriously considering putting AI into production has to do at least some manual validation. Setting up a good validation pipeline with a tool like Argilla is crucial and it can be reused for any future experiments. Note: you can use LLM-as-a-judge to automate some evals, but you always also need to validate the judge!
3. Based on this validation I can then (a) either just continue using the prompted LLM if it is accurate enough and it makes sense financially given my load; or (b) if the LLM is not accurate enough or too expensive to run in the long-run, I reuse the existing validation pipeline to annotate some additional data for fine-tuning a smaller model. This can be sped up by reusing & correcting synthetic data from the LLM (or just pure distillation).
Paper: https://arxiv.org/pdf/2409.06857
Argilla docs: https://docs.argilla.io/latest/
Argilla is also very easy to deploy with Hugging Face Spaces (or locally): https://huggingface.co/new-space?template=argilla%2Fargilla-template-space
Can this be trained?
#4 opened 4 months ago
by
umarbutler
liked
a
model
4 months ago
Conversion to tiktoken
3
#4 opened 8 months ago
by
koyfman
liked
a
model
4 months ago
Model card looks a bit messed up
1
#3 opened 4 months ago
by
umarbutler