gpt-3
public-roadmap
gpt-3 | public-roadmap | |
---|---|---|
41 | 15 | |
9,406 | 44 | |
- | - | |
3.5 | 4.0 | |
over 3 years ago | 5 months ago | |
- | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
gpt-3
-
GPT4.5 or GPT5 being tested on LMSYS?
>I wasn't talking about "state of the art LLMs," I am aware that commercial offerings are much better trained in Spanish. This was a thought experiment based on comments from people testing GPT-3.5 with Swahili.
A thought experiment from other people comments on another language. So...No. Fabricating failure modes from their constructed ideas about how LLMs work seems to be a frustratingly common occurrence in these kinds of discussions.
>Frustratingly, just few months ago I read a paper describing how LLMs excessively rely on English-language representations of ideas, but now I can't find it.
Most LLMs are trained on English overwhelmingly. GPT-3 had a 92.6% English dataset. https://github.com/openai/gpt-3/blob/master/dataset_statisti...
That the models are as proficient as they are is evidence enough of knowledge transfer clearly happening. https://arxiv.org/abs/2108.13349. If you trained a model on the Catalan tokens GPT-3 was trained on alone, you'd just get a GPT-2 level gibberish model at best.
anyway. These are some interesting papers
How do languages influence each other? Studying cross-lingual data sharing during LLM fine-tuning - https://arxiv.org/pdf/2305.13286
Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer - https://arxiv.org/abs/2404.04042
Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment - https://arxiv.org/abs/2305.05940
It's not like there is perfect transfer but the idea that there's none at all seemed so ridiculous to me (and why i asked the first question). Models would be utterly useless in multilingual settings if that were really the case.
-
What are LLMs? An intro into AI, models, tokens, parameters, weights, quantization and more
Large models: Everything above 10B of parameters. This is where Llama 3, Llama 2, Mistral 8x22B, GPT 3, and most likely GPT 4 sit.
-
Can ChatGPT improve my L2 grammar?
Are generative AI models useful for learning a language, and if so which languages? Over 90% of ChatGPT's training data was in English. The remaining 10% of data was split unevenly between 100+ languages. This suggests that the quality of the outputs will vary from language to language.
-
GPT4 Can’t Ace MIT
I have doubts it was extensively trained on German data. Who knows about GPT4, but GPT3 is ~92% of English and ~1.5% of German, which means it saw more "die, motherfucker, die" than on "die Mutter".
(https://github.com/openai/gpt-3/blob/master/dataset_statisti...)
- Necesito ayuda.
-
[R] PaLM 2 Technical Report
Catalan was 0.018 % of GPT-3's training corpus. https://github.com/openai/gpt-3/blob/master/dataset_statistics/languages_by_word_count.csv.
- I'm seriously concerned that if I lost ChatGPT-4 I would be handicapped
- The responses I got from bard after asking why 100 times… he was pissed 😂
-
BharatGPT: India's Own ChatGPT
>Certainly it is pleasing that they are not just doing Hindi, but some of these languages must be represented online by a very small corpus of text indeed. I wonder how effectively an LLM can be trained on such a small training set for any given language?
as long as it's not the main language it doesn't really matter. Besides English(92.6%), the biggest language by representation (word count) is taken up by french at 1.8%. Most of the languages GPT-3 knows are sitting at <0.2% representation.
https://github.com/openai/gpt-3/blob/master/dataset_statisti...
Competence in the main language will bleed into the rest.
- GPT-4 gets a B on Scott Aaronson's quantum computing final exam
public-roadmap
-
AI Report #4: AutoGPT And Open-source lags behind Part 2
> The google search function is also limited. For comparison, SerpAPI masterfully scrapes Google Search using a proxy network and very intelligent parsing. In experiments using SerpAPI in combination with Microsoft’s guidance module, I got much farther than AutoGPT.
Thanks for your kind words. We are working on SerpApi integration for Auto-GPT: https://github.com/serpapi/public-roadmap/issues/905
-
Get Product Data from Bing Shopping with Python and SerpApi
Add a Feature Request💫 or a Bug🐞
-
JavaScript Hotels Parser
The long-term plan of this project is to combine API and non-API solutions as SerpApi started developing support for Google Hotels so later users can choose the desired backend to work with (free with limitations or paid without limitations). SerpApi's backend could be also useful for people who don't know how to use it, for example, SerpApi pagination which could be enabled with a simple function argument pagination=True.
-
SerpApi Changelog: December, 2022
Try in the Playground | Documentation | Public Roadmap Issue
-
How to reverse engineer a JSON API on a single page application
I was debugging the Bing Image Search to help implementing our new Bing Reverse Image Search API. Initially, I've used mitmproxy because Ctrl+Shift+F in the browser dev tools haven't found the request. Then I've figured out how to filter network requests in the browser dev tools, examined the response, and made a draft data adapter.
-
When and How to use AI Solutions in your Product?
If there is a difference in one of the keys, an automated bot reports a possible issue in SerpApi Public Roadmap.
-
Scrape Brave Images with Python
You can check our public roadmap to track the progress for this API: [New API] Brave Search
-
Scrape Google Play Children (Kids) with Python
Add a Feature Request💫 or a Bug🐞
-
Web scraping Google Books Ngram Viewer with Nodejs
🗺️ [New API] Add Google Ngram Viewer API
-
SerpApi Changelog: September, 2022
Try in the Playground | Documentation | Public Roadmap Issue
What are some alternatives?
dalle-mini - DALL·E Mini - Generate images from a text prompt
axios - Promise based HTTP client for the browser and node.js
DALL-E - PyTorch package for the discrete VAE used for DALL·E.
hotels-scraper-js - Scrape Airbnb, Booking, Hotels.com from a single JavaScript module. ❗No longer maintained.
DALLE-mtf - Open-AI's DALL-E for large scale training in mesh-tensorflow.
webgpt-cli - a cli that recreates webgpt through multi shot prompting
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
serpapi-javascript - Scrape and parse search engine results using SerpApi.
v-diffusion-pytorch - v objective diffusion inference code for PyTorch.
chatGPT-telegram-bot - This is a very early attempt at having chatGPT work within a telegram bot
dalle-2-preview
pyserpZotero - serpAPI citation download, parsing, Bibtex export, and Zotero cloud upload.