Top all-time · #14722
Advanced Artificial Intelligence API
Company blog · nlpcloud.ioaidata
Advanced Artificial Intelligence API is the company blog at nlpcloud.io, writing about ai and data. Since 2021, 5 different Hacker News readers have linked it 9 times, most often “Using GPT-J and GPT-Neo, GPT-3 open-source alternatives, with few-shot learning”. No feed was found, so read it on the site itself.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link NLP Cloud's blog for posts on running open language models such as GPT-J and GPT-NeoX and on alternatives to GPT-3. One commenter called a breakdown of GPT-J and GPT-Neo functionality wonderfully written.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Advanced AI platform, for NER, sentiment analysis, emotion analysis, text classification, summarization, dialogue summarization, question answering, text generation, translation, language detection, grammar and spelling correction, intent classification, paraphrasing and rewriting, code generation,
Most-linked posts?
- Using GPT-J and GPT-Neo, GPT-3 open-source alternatives, with few-shot learning2 people · 2 mentions · first linked 2021-09-29
- A cloud version of Python spaCy to easily deploy NLP models in production2 people · 2 mentions · first linked 2021-01-19
What Hacker News says?
Totally, and that's because GPT models don't really support multilingual content. It works, but very poorly. It's the case for GPT-J, GPT-NeoX 20B, and even GPT-3. I recently integrated GPT-NeoX 20B on NLP Cloud: https://nlpcloud.io . I had hopes that non-English languages would be better supported than with GPT-J since the model was trained on 20B parameters instead of 6B parameters, but quality still leaves to be…
Comment linking /multilingual-nlp-how-to-perform-nlp-in-non-english-languages.html
on “Textsynth: Bellard's free GPT-NeoX-20B, GPT-J playground and paid API”Submitted Using GPT-J and GPT-Neo, GPT-3 open-source alternatives, with few-shot learning as a story · 24 points
HN discussionOpen alternatives to GPT-3 also seem to exist: https://nlpcloud.io/gpt-3-open-source-alternatives-gpt-j-gpt...
Comment linking /gpt-3-open-source-alternatives-gpt-j-gpt-neo.html
on “Customizing GPT-3 for Your Application”Submitted GPT-3 open-source alternatives: GPT-Neo and GPT-J as a story · 4 points
HN discussionhttps://nlpcloud.io/effectively-using-gpt-j-gpt-neo-gpt-3-al... Here's a wonderfully written breakdown of some functionality that can be achieved with gpt-j and gpt-neo - it's not ExaFunction specific, but the language models are the same. The exafunction api is fairly simple and powerful. Kudos!
Comment linking /effectively-using-gpt-j-gpt-neo-gpt-3-alternatives-few-shot-learning.html
on “Show HN: Exafunction NLP – Run models like GPT-J for 6x cheaper than OpenAI”Submitted NLP Cloud API as a story · 1 points
HN discussionHere's the ML stack I have been using for my last project: - Doing NLP with spaCy ( https://spacy.io/ ) as I consider it to be the most production ready framework for NLP - Annotating datasets with Prodigy ( https://prodi.gy/ ), a paid tool made by the spaCy team - Deploying the trained spaCy models onto NLP Cloud ( https://nlpcloud.io ), a service I helped creating - Use the models through the NLP Cloud API in prod…
Comment linking /
on “Ask HN: What is your production ML stack like? (2021)”Submitted A cloud version of Python spaCy to easily deploy NLP models in production as a story · 1 points
HN discussion