NickoSELI/raga-convo-mock4
Viewer
ā¢
Updated
ā¢
20k
ā¢
35
topsa
NickoSELI
Ā·
AI & ML interests
None yet
Recent Activity
updated
a dataset
25 days ago
NickoSELI/raga-convo-mock4
updated
a dataset
25 days ago
NickoSELI/raga-convo-mock2
updated
a dataset
25 days ago
NickoSELI/raga-convo-mock1
Organizations
None yet
NickoSELI's activity
updated
3
datasets
25 days ago
updated
a
Space
26 days ago
updated
a
dataset
26 days ago
updated
a
dataset
about 1 month ago
updated
a
model
about 1 month ago
updated
a
dataset
about 1 month ago
reacted to
davidberenstein1957's
post with ā¤ļø
3 months ago
Post
1694
You can now build a custom text classifier without days of human labeling!
š LLMs work reasonably well as text classifiers.
š They are expensive to run at scale and their performance drops in specialized domains.
š Purpose-built classifiers have low latency and can potentially run on CPU.
š 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
š LLMs work reasonably well as text classifiers.
š They are expensive to run at scale and their performance drops in specialized domains.
š Purpose-built classifiers have low latency and can potentially run on CPU.
š 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
updated
a
Space
8 months ago
updated
2
Spaces
9 months ago
liked
a
Space
9 months ago
liked
a
model
9 months ago
