Hacker News new | ask | show | jobs
by cpdomina 1289 days ago
You can call any of the huggingface models [1] using their API [2]. A few examples:

- https://huggingface.co/EleutherAI/gpt-j-6B

- https://huggingface.co/t5-base

- https://huggingface.co/facebook/opt-66b

- https://huggingface.co/bigscience/bloomz-3b

There are also other companies offering large models as a service:

- https://www.forefront.ai

- https://nlpcloud.com

- https://www.goose.ai

- https://cohere.ai/generate

[1] https://huggingface.co/models

[2] https://huggingface.co/inference-api

1 comments

I wouldn't have suggested those models. Just use a semantically fine-tuned BERT.

> GPT-3 Embeddings by @OpenAI was announced this week. I was excited and tested them on 20 datasets. Sadly they are worse than open models that are 1000 x smaller

https://twitter.com/Nils_Reimers/status/1487014195568775173

Get models here: https://sbert.net/docs/pretrained_models.html