How to build a custom text classifier without days of human labeling
โข
55
David Berenstein
davidberenstein1957
AI & ML interests
Everything NLP and knowledge graphs
Articles
Organizations
davidberenstein1957's activity
sweeet 25th place ๐
reacted to
m-ric's
post with ๐โค๏ธ๐ฅ
1 day ago
Post
3409
๐ง๐ต๐ฒ ๐ป๐ฒ๐
๐ ๐ฏ๐ถ๐ด ๐๐ผ๐ฐ๐ถ๐ฎ๐น ๐ป๐ฒ๐๐๐ผ๐ฟ๐ธ ๐ถ๐ ๐ป๐ผ๐ ๐ฆ, ๐ถ๐'๐ ๐๐๐ฏ ๐ฃ๐ผ๐๐๐! [INSERT STONKS MEME WITH LASER EYES]
See below: I got 105k impressions since regularly posting Hub Posts, coming close to my 275k on Twitter!
โ๏ธ Computed with the great dataset maxiw/hf-posts
โ๏ธ Thanks to Qwen2.5-Coder-32B for showing me how to access dict attributes in a SQL request!
cc @merve who's far in front of me
See below: I got 105k impressions since regularly posting Hub Posts, coming close to my 275k on Twitter!
โ๏ธ Computed with the great dataset maxiw/hf-posts
โ๏ธ Thanks to Qwen2.5-Coder-32B for showing me how to access dict attributes in a SQL request!
cc @merve who's far in front of me
- 9 replies
reacted to
their
post with ๐
13 days ago
Post
676
The Synthetic Data Generator now directly integrates with Argilla, so you can generate and curate your own high-quality datasets from pure natural language!
Up next -> include dataset generation for text classification.
Other suggestions? Let us know.
Space: argilla/synthetic-data-generator
Up next -> include dataset generation for text classification.
Other suggestions? Let us know.
Space: argilla/synthetic-data-generator
reacted to
their
post with โโค๏ธ
13 days ago
Post
1682
You can now build a custom text classifier without days of human labeling!
๐ LLMs work reasonably well as text classifiers.
๐ They are expensive to run at scale and their performance drops in specialized domains.
๐ Purpose-built classifiers have low latency and can potentially run on CPU.
๐ They require labeled training data.
Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.
Blog: https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback
๐ LLMs work reasonably well as text classifiers.
๐ They are expensive to run at scale and their performance drops in specialized domains.
๐ Purpose-built classifiers have low latency and can potentially run on CPU.
๐ They require labeled training data.
Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.
Blog: https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback
posted
an
update
13 days ago
Post
2056
Import any dataset from the Hub and configure your labeling tasks without needing any code!
Really excited about extending the Hugging Face Hub integration with many more streamlined features and workflows, and we would love to hear your feedback and ideas, so don't feel shy and reach out ๐ซถ๐ฝ
https://huggingface.co/blog/argilla-ui-hub
Really excited about extending the Hugging Face Hub integration with many more streamlined features and workflows, and we would love to hear your feedback and ideas, so don't feel shy and reach out ๐ซถ๐ฝ
https://huggingface.co/blog/argilla-ui-hub
reacted to
their
post with ๐๐๐ค
13 days ago
Post
3062
Vector Search (most) datasets on the Hugging Face Hub ๐ฆ
Powered by: Polars, DuckDB, Gradio and model2vec (lightning-fast embeddings by Stรฉphan Tulkens).
Should work fast enough for datasets up to 100K.
davidberenstein1957/vectorsearch-hub-datasets
Powered by: Polars, DuckDB, Gradio and model2vec (lightning-fast embeddings by Stรฉphan Tulkens).
Should work fast enough for datasets up to 100K.
davidberenstein1957/vectorsearch-hub-datasets
posted
an
update
13 days ago
Post
3062
Vector Search (most) datasets on the Hugging Face Hub ๐ฆ
Powered by: Polars, DuckDB, Gradio and model2vec (lightning-fast embeddings by Stรฉphan Tulkens).
Should work fast enough for datasets up to 100K.
davidberenstein1957/vectorsearch-hub-datasets
Powered by: Polars, DuckDB, Gradio and model2vec (lightning-fast embeddings by Stรฉphan Tulkens).
Should work fast enough for datasets up to 100K.
davidberenstein1957/vectorsearch-hub-datasets
posted
an
update
19 days ago
Post
1737
โก๏ธ LLMs do a good job at NER, but don't you want to do learn how to do more with less?
Go from ๐ข -> ๐
If you want a small model to perform well on your problem, you need to fine-tune it.
Bootstrap with a teacher model.
Correct potential mistakes to get high-quality data.
Fine-tune your student model
Go more accurate and more efficient.
Free signup: https://lu.ma/zx2t7irs
Go from ๐ข -> ๐
If you want a small model to perform well on your problem, you need to fine-tune it.
Bootstrap with a teacher model.
Correct potential mistakes to get high-quality data.
Fine-tune your student model
Go more accurate and more efficient.
Free signup: https://lu.ma/zx2t7irs
posted
an
update
about 1 month ago
Post
1682
You can now build a custom text classifier without days of human labeling!
๐ LLMs work reasonably well as text classifiers.
๐ They are expensive to run at scale and their performance drops in specialized domains.
๐ Purpose-built classifiers have low latency and can potentially run on CPU.
๐ They require labeled training data.
Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.
Blog: https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback
๐ LLMs work reasonably well as text classifiers.
๐ They are expensive to run at scale and their performance drops in specialized domains.
๐ Purpose-built classifiers have low latency and can potentially run on CPU.
๐ They require labeled training data.
Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.
Blog: https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback
reacted to
nroggendorff's
post with ๐
about 1 month ago
Post
1251
100 followers? When did that happen?
reacted to
m-ric's
post with ๐
about 1 month ago
Post
1685
By far the coolest release of the day!
> The Open LLM Leaderboard, most comprehensive suite for comparing Open LLMs on many benchmarks, just released a comparator tool that lets you dig into the detail of differences between any models.
Here's me checking how the new Llama-3.1-Nemotron-70B that we've heard so much compares to the original Llama-3.1-70B. ๐ค๐
Try it out here ๐ open-llm-leaderboard/comparator
> The Open LLM Leaderboard, most comprehensive suite for comparing Open LLMs on many benchmarks, just released a comparator tool that lets you dig into the detail of differences between any models.
Here's me checking how the new Llama-3.1-Nemotron-70B that we've heard so much compares to the original Llama-3.1-70B. ๐ค๐
Try it out here ๐ open-llm-leaderboard/comparator
- 2 replies
posted
an
update
about 1 month ago
Post
676
The Synthetic Data Generator now directly integrates with Argilla, so you can generate and curate your own high-quality datasets from pure natural language!
Up next -> include dataset generation for text classification.
Other suggestions? Let us know.
Space: argilla/synthetic-data-generator
Up next -> include dataset generation for text classification.
Other suggestions? Let us know.
Space: argilla/synthetic-data-generator
posted
an
update
about 1 month ago
Post
2495
Don't use an LLM when you can use a much cheaper model.
The problem is that no one tells you how to actually do it.
Just picking a pre-trained model (e.g., BERT) and throwing it at your problem won't work!
If you want a small model to perform well on your problem, you need to fine-tune it.
And to fine-tune it, you need data.
The good news is that you don't need a lot of data but instead high-quality data for your specific problem.
In the latest livestream, I showed you guys how to get started with Argilla on the Hub! Hope to see you at the next one.
https://www.youtube.com/watch?v=BEe7shiG3rY
The problem is that no one tells you how to actually do it.
Just picking a pre-trained model (e.g., BERT) and throwing it at your problem won't work!
If you want a small model to perform well on your problem, you need to fine-tune it.
And to fine-tune it, you need data.
The good news is that you don't need a lot of data but instead high-quality data for your specific problem.
In the latest livestream, I showed you guys how to get started with Argilla on the Hub! Hope to see you at the next one.
https://www.youtube.com/watch?v=BEe7shiG3rY
posted
an
update
about 1 month ago
Post
1213
Thursday 10 October 17:00 CEST, I will show a good way to get started with a text classification project on the Hugging Face Hub with Argilla and Setfit.
Signup here: https://lu.ma/31mecp34
Signup here: https://lu.ma/31mecp34
reacted to
their
post with ๐ฅ
about 2 months ago
Post
1134
Why is argilla/FinePersonas-v0.1 great for synthetic data generation? It can be used to synthesise realistic and diverse data of the customer personas your company is interested in!
Dataset: argilla/FinePersonas-v0.1
Example usage: https://distilabel.argilla.io/dev/sections/pipeline_samples/examples/fine_personas_social_network/
Dataset: argilla/FinePersonas-v0.1
Example usage: https://distilabel.argilla.io/dev/sections/pipeline_samples/examples/fine_personas_social_network/
- 1 reply