mothcamp
Re:A simple guide to fine-tuning Llama 2
on Tuesday July 25, 2023 @11:43AM (#36864009)
Awesome! To protect your privacy on HN, please email [email protected] and let me know whether you prefer getting on a call or keep things in writing. Looking forward to hearing from you!
Re:A simple guide to fine-tuning Llama 2
on Tuesday July 25, 2023 @09:55AM (#36862246)
I imagine it's a company similar to Bulletin Intelligence. Would you be open to discussing your experiences in this industry?
Re:Ask HN: Best examples of software documentation that you've come ac...
on Thursday February 16, 2023 @12:18PM (#34821729)
Slack: https://api.slack.com/docs
In addition to being thorough, it has personality.
Re:Show HN: Explore careers that you don't know even exist
on Wednesday February 15, 2023 @11:09AM (#34805744)
The vibes I got were dystopian.
I positioned myself as someone seeking help, and the bot came across like an HR person play-acting empathy and care, and couldn't wait for me to leave the office. It came down to (1) do your research, (2) make a list, (3) take courses, (4) be aware of barriers.
Re:Ask HN: Share Your YouTube Channel
on Sunday February 05, 2023 @02:46PM (#34668387)
https://www.youtube.com/@nitin_punjabi/videos
Just a place to host my NLP course. Don't know whether I'll do anything further.
Re:Show HN: Natural Language Processing Demystified (full release/no s...
on Friday December 02, 2022 @06:33AM (#33829174)
Thanks. It's all statically-generated pages with NextJS and Tailwind.
Re:Show HN: Natural Language Processing Demystified (full release/no s...
on Thursday December 01, 2022 @01:07PM (#33820066)
It's for anyone who wants to learn NLP such that they get (a) an understanding of what's going on under the hood and (b) knowledge of how to get stuff done.
So the ideal outcome is someone who gets an end-to-end view from theory/concept to implementation.
If someone just wants to learn how to use tools/frameworks, I'd stick to the Colab notebooks. If someone's already experienced in ML and wants to learn something NLP-specific, I'd skip around to see what's interesting.
Re:Show HN: Natural Language Processing Demystified (full release/no s...
on Thursday December 01, 2022 @11:06AM (#33818139)
Yeah, I can see that being the case for specialized domains. With state-of-the-art models widely available to the public, knowledge of the domain and its workflows, and fine-tuning models to suit the domain will probably be your edge.
Re:Show HN: Natural Language Processing Demystified (full release/no s...
on Thursday December 01, 2022 @10:38AM (#33817685)
I did record all voice tracks, yeah. If I do this again, I'll probably use a lot of generative tools now. :-D
Hope you find the transformers module useful!
Re:Show HN: Natural Language Processing Demystified (full release/no s...
on Thursday December 01, 2022 @10:31AM (#33817557)
You could start by looking into either multitask transformers or really general seq2seq models like T5. With T5, for example, it just learns to transform one text sequence into another. So you could fine-tune T5 to produce your target sequence, but rather than outputting an explicit Python list of tuples, it would output a string that looks like a sequence of tuples.
Or maybe skip all that and outsource it to GPT: https://imgur.com/a/BQv6C3K
Re:Show HN: Natural Language Processing Demystified (full release/no s...
on Thursday December 01, 2022 @09:45AM (#33816864)
Your time. That's it.
Re:Show HN: Natural Language Processing Demystified (full release/no s...
on Thursday December 01, 2022 @09:26AM (#33816610)
Really appreciate that. Finding that balance was one of the hardest parts of building this course.
Show HN: Natural Language Processing Demystified (full release/no sign-up req'd)
Link: https://www.nlpdemystified.org/Hi HN:After a year of work, I've published my free NLP course. The course helps anyone who knows Python and a bit of math go from the basics to today's mainstream models and frameworks.I strive to balance theory and practice, so every module consists of detailed explanations and slides along with a Colab notebook putting the ideas into practice (in most...
Re:Does HN have anti-duplication protection?
on Tuesday November 29, 2022 @02:28PM (#33792045)
Will do. Thank you.
Does HN have anti-duplication protection?
Six months ago, I published part one of my NLP course and submitted this link: https://news.ycombinator.com/item?id=31421232This morning, I wanted to share that I released the FULL course (same URL) but every time I hit submit, it redirects me to my previous submission.Is this some anti-duplication protection in action? Does my account not have posting privileges?
Re:Show HN: Natural Language Processing Demystified (Part One)
on Wednesday May 18, 2022 @11:12AM (#31423795)
I agree. I think having linguistics knowledge can help especially in applied situations. Linguistics knowledge can help create fallback systems when an ML system fails, or help build rules to amplify or dampen the confidence of a response from an ML system, or aid in the engineering of a system (all that comes before or after the ML blackbox).
Sort of like an algorithmic trader knowing market microstructure intimately (versus only pure statistics).
Re:Show HN: Natural Language Processing Demystified (Part One)
on Wednesday May 18, 2022 @10:55AM (#31423573)
Thank you. Yep. It's all statically-generated pages using Next.js with a single Next.js API route for the subscription. All hosted on Netlify.
Re:Show HN: Natural Language Processing Demystified (Part One)
on Wednesday May 18, 2022 @09:17AM (#31422389)
In addition to Jurafsky and Martin (https://web.stanford.edu/~jurafsky/slp3/), I also like Emily Bender's book:
https://www.goodreads.com/book/show/18128399-linguistic-fund...
Bender's book is NOT an end-to-end text though imo. It's more a central jumping off point. So you can read about a concept and if it sounds interesting, search more about it.
Re:Show HN: Natural Language Processing Demystified (Part One)
on Wednesday May 18, 2022 @06:56AM (#31421240)
Hi HN:
I published part one of my free NLP course. The course is intended to help anyone who knows Python and a bit of math go from the very basics all the way to today's mainstream models and frameworks.
I strive to balance theory and practice and so every module consists of detailed explanations and slides along with a Colab notebook (in most modules) putting the theory into practice.
In part one, we cover text preprocessing, how to turn text into numbers, and multiple ways to classify and search text using "classical" approaches. And along the way, we'll pick up useful bits on how to use tools such as spaCy and scikit-learn.
No registration required: https://www.nlpdemystified.org/
Show HN: Natural Language Processing Demystified (Part One)
https://www.nlpdemystified.org/
Hi HN:I published part one of my free NLP course. The course is intended to help anyone who knows Python and a bit of math go from the very basics all the way to today's mainstream models and frameworks.I strive to balance theory and practice and so every module consists of detailed explanations and slides along with a Colab notebook (in most modules) putting the theory into practice.In part...