[HN Gopher] Few-Shot Learning in Practice: GPT-Neo & 'HuggingFac...
___________________________________________________________________
Few-Shot Learning in Practice: GPT-Neo & 'HuggingFace' Accelerated
Inference API
Author : homarp
Score : 51 points
Date : 2021-06-04 16:37 UTC (6 hours ago)
(HTM) web link (huggingface.co)
(TXT) w3m dump (huggingface.co)
| spywaregorilla wrote:
| Hmm I don't work in this space too often, but wouldn't the
| maximum likelihood estimator of a oneshot example, saying telling
| it king => queen, hoping to learn male to female transitions...
| wouldn't that just be the simple linear transformation between
| the two embeddings?
|
| I'm sure a few shot model can be a little more nuanced but I'm
| not sure I have any intuition about what that transformation
| looks like.
| konfuzio wrote:
| Good to see that few shot learning is now even easier using the
| widget. We have had good results with writing emails and reported
| about it in our blog: https://www.helm-nagel.com/open-sourced-
| gpt-Neo-writes-indiv...
___________________________________________________________________
(page generated 2021-06-04 23:01 UTC)