ssary/XLM-RoBERTa-German-sentiment
Text Classification
•
Updated
•
240
•
9
Oliver Guhr
oliverguhr
AI & ML interests
Voice Interfaces, Robotics, Deep Learning
Recent Activity
liked
a model
12 days ago
ssary/XLM-RoBERTa-German-sentiment
liked
a model
about 1 month ago
openGPT-X/Teuken-7B-instruct-research-v0.4
liked
a model
about 1 month ago
jinaai/jina-embeddings-v2-base-de
Organizations
oliverguhr's activity
liked
a
model
12 days ago
liked
2
models
about 1 month ago
liked
a
model
2 months ago
Adding `safetensors` variant of this model
#1 opened 2 months ago
by
SFconvertbot
commented
a
paper
3 months ago
upvoted
a
paper
3 months ago
updated
a
collection
3 months ago
liked
a
dataset
3 months ago
reacted to
MoritzLaurer's
post with 🔥👍
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
updated
a
collection
4 months ago
liked
3
models
4 months ago
liked
a
Space
4 months ago
liked
2
models
4 months ago
liked
a
model
5 months ago
liked
a
Space
5 months ago