Datasets:

Modalities:
Text
Formats:
parquet
Languages:
English
ArXiv:
Libraries:
Datasets
pandas
License:
conversations
listlengths
2
2
[ { "from": "human", "value": "Can I auto-forward my Gmail to another address?\n\nI'm kind of paranoid about my email and I don't want it to be on Google's servers only. Especially after my account got hacked and all my email got deleted.\nSo I would like to auto-forward my Gmail to another address, but are there any settings I have to enable?\n\n\n" }, { "from": "gpt", "value": "In Gmail: Settings → Forwarding and POP/IMAP → Forward a copy of incoming mail to...\n" } ]
[ { "from": "human", "value": "How do I delete all my mail from my Gmail account?\n\nI want to clear my mail from my Gmail account, but don't feel like selecting every message (also the archived ones).\nIs there an easy way to delete all my mail from Gmail without having to delete my account?\n\n\n" }, { "from": "gpt", "value": "Go to your \nAll mail view, \nand click \"Select all\" (or the drop down option All from the checkbox far left of Archive | Spam | Delete buttons). \nUnderneath the | Archive | Spam | Delete | + | - | Move to Inbox | Labels | More |\nbuttons... \nYou'll see a message appear in a yellow bar that says:\n\nAll 100 conversations on this page are selected. Select all 73795 conversations in All Mail\n\nClick on the \"Select all conversations\" link on the right side of the message, then click delete. \nThe actual deletion process may take a very, very long time, during which you will be unable to use Gmail or log in (don't worry, it's still churning away in the background, even if it gives you an error!)\nWhen it's done, all conversations (except spam) will be in the trash and you should see a message that says \"You don't have any mail! Our servers are feeling unloved.\" \nNow just empty the trash and delete all spam, and your account is now empty.\n" } ]
[ { "from": "human", "value": "How do I delete my Facebook account?\n\nI don't trust Facebook's new privacy settings and have decided to delete my account, but I can't find the kill switch.\nDoes anyone know how I can delete my Facebook account?\n\n\n" }, { "from": "gpt", "value": "from here:\n\nGo here:\nhttp://www.facebook.com/help/delete_account\nClick \"Delete My Account\" and follow the instructions.\nYour account will be deactivated for two weeks, and if you DO NOT USE FACEBOOK IN ANY WAY during that period, your account is permanently deleted.\n\n" } ]
[ { "from": "human", "value": "How can I upload videos > 15min to YouTube?\n\nI see that some YouTube users have quite lengthy videos. But if I ever try to upload a video of length more than 15 min, YouTube stops me. How can I get more privileges in YouTube?\n\n\n" }, { "from": "gpt", "value": "You can't without becoming a partner.\n\nThe upload limit on YouTube videos has been increased from 10 minutes to 15 minutes. One of the reasons we can increase the video time limit is that we've made incremental improvements to our Content ID technology that helps content owners manage their videos on YouTube. We look forward to increasing the upload limit as Content ID continues to evolve and become even more sophisticated.\n\nIf you want to upload videos longer than 15 minutes, try another site such as Vimeo, Blip.tv or Viddler. You could also host it yourself using JWPlayer and a CDN such as CloudFront. As Even Mien said in the comments, you could also see if you can become a partner.\n" } ]
[ { "from": "human", "value": "How can I control who follows me on Twitter?\n\nI tend to get a bunch of emails every week that say:\n\nJaneDoe (JaneDoe343) is now following\n your tweets on Twitter.is now\n following you.\nA little information about JaneDoe:\n0 followers\n1 tweet\nfollowing 483 people\n\n\nI prefer my followers to be real people, so is there any way I can control who follows me?\n\n\n" }, { "from": "gpt", "value": "There are some options:\n\nYou might want to make your account protected. If you do this, you can control who gets to follow you and who doesn't. However this also means that none of your tweets will be public, so people will have to follow you first (and you will have to accept them) before they can see your tweets.\nYou can block a person you don't like. Just go to their profile and click the block link in the sidebar.\n\n" } ]
[ { "from": "human", "value": "How do I make Facebook block a friend’s Mafia Wars updates?\n\nI like Facebook to connect with friends, but I don't like the way their favorite games spam me.\nThey just keep giving me Mafia Wars updates!\nIs there any way to block a friend's Mafia Wars update? Or any other Facebook game for that matter.\n\n\n" }, { "from": "gpt", "value": "You can open the game at http://apps.facebook.com/inthemafia/. Find the \"Block Application\" link and follow the instructions. Further updates from Mafia Wars will not be seen on your account. If you're interested in just blocking a particular user's updates, you can block the person by visiting their profile and doing the same thing on that page, however you will effectively be blocking ALL of their updates and not just their Mafia Wars updates.\n" } ]
[ { "from": "human", "value": "How do I transfer my blog posts from Google's Blogger to WordPress?\n\nI have a blog on Google's Blogger, but now I want to move to WordPress.\nIs there an easy way to transfer all my old blog posts from Blogger to WordPress?\n\n\n" }, { "from": "gpt", "value": "I am using Wordpress 3.0 so I am not sure if this applies to previous versions of WP or not. \nIn the WP admin, go to Tools > Import. Then you'll see a list of import tools you can install and use.\n\n" } ]
[ { "from": "human", "value": "How do I sync Google Calendar with my Outlook Calendar?\n\nAt work we use Outlook, but I want an easy way to sync it with my private Google Calendar.\nHowever, I tried looking at the Outlook (2010) settings and couldn't find how to make a link.\nSo how do I sync my Google Calendar with my Outlook one?\n\n\n" }, { "from": "gpt", "value": "You may want to take a look at Google's Calendar Sync:\n\nGoogle Calendar Sync allows you to sync events between Google Calendar and Microsoft Outlook Calendar. You'll be able to determine the direction of information flow, as well as the sync frequency. Staying on top of your Google Calendar and Microsoft Outlook Calendar events has never been easier! Here's some good information to know to help you get started with Google Calendar Sync.\n\nIt lists as only being compatible with Outlook 2003 and 2007, so I'm not sure if it works with Outlook 2010.\n" } ]
[ { "from": "human", "value": "How do I get the phone numbers of my Facebook Friends?\n\nThere was a time that somehow Facebook synced to my phone and that was great but I did not want all of them. How can I manually select the Facebook numbers and then export it to my phone via Contacts or Microsoft Exchange ? Where is this option ?\n\n\n" }, { "from": "gpt", "value": "On Facebook: \n\nClick the \"Account\" dropdown menu.\nClick \"Edit Friends\"\nLook on the left-side menu for \"Phonebook\".\n\nAll friends with their phone numbers entered will appear in the list.\n" } ]
[ { "from": "human", "value": "How to use GPG with Gmail?\n\nI would like to read and write GPG encrypted mails within Gmail. I found FireGPG, but the support for Gmail has been discontinued (and I am using Google Chrome as a browser).\nWhat is the most practical way to achieve this?\n\n\n" }, { "from": "gpt", "value": "Unfortunately, there is currently no reasonable way to use GPG/PGP from within Gmail directly. The only two options are to encrypt the message manually from a client-side tool, pasting the result into Gmail when you're done, or to use a desktop mail client with GPG integration (such as Thunderbird + Enigmail) to send messages you need to be encrypted. Decrypting would likewise entail downloading the message from Google as raw source, running it through the desktop client to decrypt, and reading it there.\n" } ]
[ { "from": "human", "value": "How can I delete my Twitter account?\n\nI've decided I don't want to use Twitter any more - how can I delete my account?\n\n\n" }, { "from": "gpt", "value": "To deactivate your account:\n\nLog in to Twitter\nGo to Settings\nClick Deactivate my account at the bottom of the page\nVerify that you really want to do it and voila, it's done.\n\nMore information in Twitter's Help pages\n" } ]
[ { "from": "human", "value": "Is there any way to use Gmail storage in other Google services?\n\nIt's unlikely that I'll ever have more than 1GB of email. However, I do have more than 1GB of photos (Picasa) and more than 1GB of files (Google Docs). Is there any way to use the storage from Gmail in these other services? Or, to possibly answer my own question, is Google just marketing the available storage of Gmail by banking on the fact that nobody is going to use that much (whereas it would be much easier for people to fill up their Picasa accounts)?\n\n\n" }, { "from": "gpt", "value": "The only time that storage is shared between the other Google products is when additional space is purchased: https://www.google.com/accounts/purchasestorage\nIn the Google Picasa help section about Google Storage they say that \"Free storage space is specific to each product. Picasa Web Albums offers 1 GB of storage for photos and videos only. Gmail provides 7+ GB (and counting) which is reserved just for Gmail messages. Docs gives you 1 GB for everything: all of your docs, spreadsheets, presentations, and uploaded files. Free storage from one product cannot be used by or transferred to another product.\"\n-- EDIT -- \nAs Al Everett pointed out the storage is now combined between Google's properties.\n" } ]
[ { "from": "human", "value": "I want to receive the tweets of everyone I follow as emails. How do I configure that?\n\nI suspect this might require a 3rd party application. \nThere is no way that I would want SMS notifications to my phone (which is almost what I'm looking for).\nAnd if I could get emails just for particular users that would be even better.\n\n\n" }, { "from": "gpt", "value": "You could try TweetyMail.com. From their FAQ: \n\ntweetymail is a complete email interface to Twitter.\n\n" } ]
[ { "from": "human", "value": "Can I access Gmail through SSL?\n\nIs there a way to access Gmail securely over SSL?\n\n\n" }, { "from": "gpt", "value": "Yes, just add an \"s\" to the http in the address bar - so to get to Gmail over SSL, type in:\nhttps://www.gmail.com\nYou can also change a setting in Gmail to require your account to use SSL:\n\nWe've recently made the 'Always use https' setting the default behavior in Gmail (the default used to be http). Here's some background: If you sign in to Gmail via a non-secure Internet connection, like a public wireless or non-encrypted network, your Google account may be more vulnerable to hijacking. Non-secure networks make it easier for someone to impersonate you and gain full access to your Google account, including any sensitive data it may contain like bank statements or online log-in credentials. Accordingly, we enable the 'Always use https' option in Gmail by default. HTTPS, or Hypertext Transfer Protocol Secure, is a secure protocol that provides authenticated and encrypted communication.\n\nIn your Gmail settings, under the General tab, select \"Always use https\":\n\n" } ]
[ { "from": "human", "value": "How do I get rid of advertisements on the right side on Gmail?\n\nNot only am I inundated with ads in Gmail, but they seem to be reading my mind.\nIs there any way to turn this off or otherwise change this \"tracking\"?\n\n\n" }, { "from": "gpt", "value": "The Firefox extension AdBlock Plus removes them just fine, although the equivalent in Chrome does not.\nRegarding what you call \"tracking\", that is just software finding keywords in your emails and displaying appropriate ads. Obviously no personal information is given to advertisers and no-one is reading your emails.\n" } ]
[ { "from": "human", "value": "Is there any way to script a Google Docs spreadsheet?\n\nI have a really complex spreadsheet in Google Docs, and while it works, having the ability to script it a bit (à la VBA in Microsoft Office) would make it a lot cleaner. I heard that this is doable in Google Apps, but I can't find it in Google Docs. Is this possible? Or is this something only Office can do?\n\n\n" }, { "from": "gpt", "value": "Yep its called Google Apps Script.\nThey just had a Apps Script Hackathon! They have some good examples and tutorials on the resource page. Someone also coded \"Game Of Life\" in a script :)\nThey also had a talk at Google I/O about it.\n" } ]
[ { "from": "human", "value": "How hard is it to manage a TypePad blog? Should I host it myself or get hosted service?\n\nI have had difficulties in the past using Wordpress and have been thinking about moving to Typepad.\nHow difficult is it to manage a Typepad installation? Should I just install it myself on a shared host or should I pay for the hosted service? What sorts of limitations does the hosted service impose?\n\n\n" }, { "from": "gpt", "value": "Managing Typepad is extremely easy. I've used them extensively in the past for our corporate blog, and been fairly happy with their service. The only complaint I've had is that they're somewhat barebones, feature-wise, in exchange for very high uptime and a very simple user interface.\nAs far as I know, Typepad doesn't even offer a host-it-yourself service; that's part of their value: they host it for you. The advantage over a service that does do self-hosting (such as Blogger) is that you don't need to worry about maintaining your own server, handling bandwidth, and so on. The downside, obviously, is that you'll pay Typepad rates for hosting media, which are probably a bit higher than what you'd pay for using a shared host.\n" } ]
[ { "from": "human", "value": "How do I ensure that what I post on Facebook stays private?\n\nOn Facebook, how should I adjust my privacy settings so that my posts stay private?\n\n\n" }, { "from": "gpt", "value": "Honestly, if you are really concerned with the privacy of your account it may be better to not post anything you would not want to be public. \n" } ]
[ { "from": "human", "value": "Can I change my Gmail email address?\n\nI have a stupidly long email address on Gmail and would like to get it changed, or even just get a new one, but I can't see how. As soon as I log in on Google it knows who I am and signing up for a new email doesn't work.\nIs there a way to get my email address changed or get a new one that I can then switch to?\nEdit 2 July 2010:\nI need to clarify the question because I haven't had an answer to what I want to achieve. I want to change the primary address on my Google account (https://www.google.com/accounts/ManageAccount). When I click the link to edit \"Email addresses\", the primary email is shown without an option to switch/change it. When I try add a new Gmail email address, it says\n\n\"You cannot associate a Gmail address with your Google Account.\"\n\nI want the primary email address on my Google account to be a shorter Gmail email address so that I can eventually retire the existing email address.\n\n\n" }, { "from": "gpt", "value": "You can logout of your Gmail account, and then sign up for a new account. Once you've created an account, go back to your original account and forward everything to the new account. \n" } ]
[ { "from": "human", "value": "How do I search within someone's tweets?\n\nI remember Jeff Atwood (@codinghorror) had posted a tweet about a new website, but I can't seem to find the link.\nIs there any way I can search within someone's tweets to find that link?\n\n\n" }, { "from": "gpt", "value": "Remy Sharp wrote a website application that will search your, or someone else's tweets without the limitations Twitter imposes so you can search far further back in time. It's at http://snapbird.org/.\n" } ]
[ { "from": "human", "value": "How do I re-activate my Twitter account using the same email address?\n\nI deleted my Twitter account, and now I can't create a new one with the same email address!\nHow do I get a new Twitter account with the same email address?\n\n\n" }, { "from": "gpt", "value": "I ran into this recently, and I thought this would be a good question to answer here.\nOne way that worked for me was to create an new twitter account with a different email address, and then once that account was active I changed the email address on the account back to the old email address.\nUseful tip for me.\n" } ]
[ { "from": "human", "value": "Alternatives to plus-addressing?\n\nMany email services, including gmail, allow you to create throwaway email addresses by appending a tag of the form +anything after the username component of your email - but many sites reject such addresses as invalid. Are there any services which offer a similar service, but using a schema that's less likely to be rejected? I know about the gmail period-insertion trick, but it's hard to remember what I created the address for with that one.\n\n\n" }, { "from": "gpt", "value": "Update 2012-09-28: tempalias is no longer running; the source code is available though.\nIf you simply need a disposable address, tempalias provides a very nice service that will give you a disposable address that expires after either a certain number of messages or a certain amount of time has passed.\nIf you care about this kind of thing, tempalias is open-source, so you can grab the source and be somewhat more confident that they themselves aren't going to do anything nefarious with your email address.\n" } ]
[ { "from": "human", "value": "For a software development project, what is the best type of wiki?\n\nI am trying to set up a wiki/management system for a software project and keep getting confused by the myriad of options available.\nI have seen TWiki and Plone before, which bill themselves as enterprise level components. Would they be better to use than something like, say, MediaWiki?\nWhat are some other suggestions for wiki/management software?\n\n\n" }, { "from": "gpt", "value": "You really can't beat Confluence, especially for $10 (for 10 or fewer users). We use it at my job and it is really fantastic. The organization takes a little getting used to, though.\n" } ]
[ { "from": "human", "value": "How to forward multiple emails in Gmail\n\nIs it possible to forward multiple emails in Gmail without doing each one individually?\n\n\n" }, { "from": "gpt", "value": "If they're all in a single conversation, then yes: click the Forward All link in the top right when viewing the conversation. Otherwise, no, you cannot bulk-forward random emails.\n\nIn newer versions of Gmail this has moved to the More button under Forward All, and is only visible when you are viewing a conversation of stacked email (stacked by title replies):\n\n" } ]
[ { "from": "human", "value": "Select All Friends in Facebook\n\nHow does one select all friends when trying to invite them into groups, etc.?\n\n\n" }, { "from": "gpt", "value": "Click on the invite button, paste this code in to your address bar:\n javascript:elms=document.getElementById('friends').getElementsByTagName('li');for(var fid in elms){if(typeof elms[fid] === 'object'){fs.click(elms[fid]);}}\n\nand hit enter. All friends will be selected, enjoy!\n" } ]
[ { "from": "human", "value": "Is there a web application that allows you to set up a wiki in 10 minutes?\n\nI've attempted to set up a wiki a couple times but left it go because the complexity overcame the time I had to do it.\nIs there a web application that allows you to easily set up a free wiki in 10 minutes the same way wordpress.com allows you to set up a free blog in 10 minutes?\n\n\n" }, { "from": "gpt", "value": "Google Sites (http://sites.google.com) lets you set up a free wiki really quickly. It's a really powerful system with lots of cool features. We use it for our companies internal wiki and it works really well.\nThe sites you create can be private or public.\n" } ]
[ { "from": "human", "value": "URL shortening web services/web sites\n\nDoes it matter which URL shortening web service you use when shortening URLs? Why will one choose, say TinyUrl over any other?\nAnd is their a lifespan for the shortened URL, will there be a guarantee that it will always be available after it is created?\n\n\n" }, { "from": "gpt", "value": "Jeff Atwood wrote that URL shortening is destroying the web. His argument is that URL shortening distorts PageRank.\n\nThe internet is the house that\n PageRank built, and it's all\n predicated on hyperlinks. Once you\n start making every link your special\n flavor of \"shortened\" link, framing\n the target content -- heck, maybe\n wrapping it in a few ads for good\n measure -- you've completely turned\n that system on its head.\n\n" } ]
[ { "from": "human", "value": "How do I delete my Gmail account?\n\nI've got an old GMail account I hardly use and want to delete it. What do I need to do?\n\n\n" }, { "from": "gpt", "value": "Check out this page on mail.google.com\n\nClick Settings at the top of any Gmail page, and open the Accounts and Import tab.\nClick Google Account settings.\nClick Edit next to My products on the right side.\nClick Remove Gmail permanently.\n\n" } ]
[ { "from": "human", "value": "How can I be certain that a URL-shortened link I click isn't going to send me to a dangerous or unwanted site?\n\nWhen I see a shortened URL, I'm always hesitant to click it because I don't know where the link is going to go. (In the worst case, it may lead to an XSS exploit against a site that I'm logged in to)\nHow can I tell where the link is going to go?\nFor example, if I see a link to http://tinyurl.com/3yjnm7y I can go to http://preview.tinyurl.com/3yjnm7y and see where the link is going to send me.\nHow can I do the same for other popular URL shortening services (like bit.ly or goo.gl)?\n\n\n" }, { "from": "gpt", "value": "You could use a service like Unshorten\n\nServices supported: TinyURL.com, SnipURL.com, NotLong.com, Metamark.net, zURL.ws and many others.\n\n" } ]
[ { "from": "human", "value": "Can I merge two conversation threads in Gmail?\n\nI really like that gmail keeps related email messages in one \"thread\" for easy access. But sometimes an email message gets left out. (I suspect the senders email client is misbehaving.)\nIs there a way to tell Gmail that I want this email message to belong to an ongoing conversation?\n\n\n" }, { "from": "gpt", "value": "No, there isn't. You can mute a thread, but you can't cleanly merge them.\nOne thing you can do: forward an orphaned email to yourself as a response to the thread you want it to be a part of, then delete the original. That won't force your sender to keep things together, nor is it particularly automated, but for reading/archiving purposes it may fit your needs.\n" } ]
[ { "from": "human", "value": "Is Google Voice available outside the United States?\n\nI live in Germany now. I got an invitation for Google Voice, but was unable to make use of it since my location was outside the U.S.\nAny idea when Google Voice will start to become available in Europe? In Germany, for instance?\n\n\n" }, { "from": "gpt", "value": "Lifehacker covered this - you require a US number to terminate calls to, however you can set up a SIP based one that can be used to receive calls anywhere you have an Internet conncetion.\n" } ]
[ { "from": "human", "value": "What's a good site for getting answers to computer software or hardware problems?\n\nI'm looking for a site where I can ask questions about a computer problem I have - one where I can get a reliable answer quickly.\nIs there such a site?\n\n\n" }, { "from": "gpt", "value": "Try SuperUser. From the FAQ:\n\nSuper User is for computer enthusiasts\n and power users. If you have a\n question about\n\ncomputer hardware\ncomputer software\n\n\n" } ]
[ { "from": "human", "value": "Can YouTube videos be viewed without using the Adobe Flash Player plugin?\n\nCan YouTube videos be viewed without using the Adobe Flash Player plugin? If so, what other specific software is necessary?\n\n\n" }, { "from": "gpt", "value": "Sure! You can use the HTML5 version of YouTube.\nAll you need is a web browser that supports both the video tag in HTML5 and either the h.264 video codec or the WebM format (with VP8 codec). These include:\n\nFirefox (WebM enabled version available here)\nGoogle Chrome (h.264 supported now, WebM enabled version available via Early Release Channel)\nOpera (WebM enabled version available here)\nApple Safari (h.264, version 4+)\nMicrosoft Internet Explorer with Google Chrome Frame installed (Get Google Chrome Frame)\n\n" } ]
[ { "from": "human", "value": "How do I get rid of \"On Behalf Of\" from my sent Gmail messages?\n\nI have a Google Apps account with 1 primary domain and a secondary alias domain (let's say example.co.uk and example.com). When I send emails from the alias domain, the receiving person sees the sender as \"alex@example.co.uk On Behalf Of alex@example.com\", which is a bit messy. How do I get rid of this?\n\n\n" }, { "from": "gpt", "value": "To do this, you need to set up Gmail to send emails via an \"external\" mail server. However, since the alias domain is already registered with Google, you can in fact set this \"external\" server to their servers and have it work just fine!\n\nGoogle Workspace Admin -> Apps -> Google Workspace -> Gmail -> End user access -> Enable Allow per-user outbound gateways in Domain admin.\nGmail -> Settings -> Accounts -> Edit Info (on alias account) -> Next Step -> Send through example.com SMTP servers (recommended for professional domains)...\nSMTP Sever: smtp.gmail.com, Port 465\nUsername: alex@example.co.uk (Note: not the alias domain login, but your main Gmail login)\nPassword: (Password for the above account)\nSelect Always use a secure connections (SSL) when sending mail.\n\nIf you don't have this other domain added as an alias and are just sending from an additional email address you'll have to send via the email servers of this other domain.\n(Yes, I know I answered my own question, but it took me an age to figure this out, so I wanted to share it!)\n" } ]
[ { "from": "human", "value": "How do you get Google to retrieve your hacked and deleted emails?\n\nMy Gmail account was hacked a while ago, and because the hacker setup a forward that deleted as it worked, I lost a month's worth of emails. Google help (oxymoron) said that I could never get the emails back, but of course we know they keep everything forever.\nSo does anyone know a method to get Google to restore the emails?\nI'm looking for some customer service trick, or secret email or phone number, or anything.\n[Yes, I realize since they've admitted that they'll give anything to the Feds that they ask for, I could play that angle, but I'm not looking to go there.]\n\n\n" }, { "from": "gpt", "value": "Their customer service is notoriously horrible. If you get a person on the phone, they will simply direct you to a web page or ask to send in the answer by email.\nI'll mention gethuman.com but if you call the Google number, they just give you instructions that point you back to the internet.\nIf you want a response, I would suggest filing a claim against them in small claims court. It won't cost much, and they'll be forced to respond. IANAL, but you probably have to sue for \"damages\" which in this case would be money, so they could also just pay you and not give you the information you seek. They could also prove that you did actually 'delete' the info and then the judge might throw it out. But at least you'd get to an actual human who could help you (or at least tell you they don't have the information).\nhttp://www.huffingtonpost.com/aaron-greenspan/why-i-sued-google-and-won_b_172403.html\n" } ]
[ { "from": "human", "value": "Is it possible to sort your email in Gmail by something other than the date received?\n\nI want to sort my email in Gmail by the sender, rather than the date received, is there a way to do this?\n\n\n" }, { "from": "gpt", "value": "Not yet. This feature is still on suggest list of feature for Gmail.\nSuggest a feature for Gmail\n" } ]
[ { "from": "human", "value": "How to remove the left tab on iGoogle\n\nThe iGoogle pages now have \"tabs\" on the left side. I only use one tab, ever, so I don't really have any use for them. Is there a way to minimize them so they don't take up a bunch of space?\n\n\n" }, { "from": "gpt", "value": "As far as I can tell, this doesn't seem possible via iGoogle's settings. A lot of people did not seem to like this decision when it was rolled out (google discussion thread) and has been asked quite a few times in support (you'll find some suggestions on how to get around this here). To summarize info that is in that thread, you will need to run some script/extension/addon to remove the tabs which are browser specific of course. For example, \nIf you are using IE7 with add-ons via IE7Pro: Toggle iGoogle Tabs\nIf you are using Firefox: iGoogle Tab Remover\nIf you are using Google Chrome: iGoogle tab remover for Chrome \nOther browsers? Not too sure of but other people can probably add to the list.\n" } ]
[ { "from": "human", "value": "Is it possible to exclude or only follow certain friends in your Facebook wall feed?\n\nI'd like to limit my wall feed in Facebook to only show the statuses or activity of certain friends and groups. How can I do that?\n\n\n" }, { "from": "gpt", "value": "Hover your mouse cursor over a news story posted by somebody you no longer wish to receive updates from - you should see the word 'Hide' appear in the top right corner. Click the word 'Hide' and then select 'Hide NAME' to remove future updates from that person.\nAlternatively, you can create lists of people e.g. friends, family, colleagues, members of a sports team etc by going to the 'Friends' menu on the left sidebar. You can then select one of these lists to view only new stories and status updates from people in those lists.\n" } ]
[ { "from": "human", "value": "Is there a way for to store bookmarks and favorites so that I can access from more than a single computer?\n\nI have a large number of bookmarked sites and links that I want to be able to access on other computers that I use. Is there a way for me to share or access these without having to sync them by hand?\n\n\n" }, { "from": "gpt", "value": "You can do this in Firefox and several other browsers using a plugin called Xmarks, in Safari using MobileMe, or in Chrome with Google's built-in Chrome Sync (in the Preferences menu).\n" } ]
[ { "from": "human", "value": "Is there a way I can use my Facebook chat from within Gmail?\n\nI like chatting with people through my Gmail account for a number of reasons, but mostly because these chats are archived and searchable. Is it possible to use my Facebook chat from within Fmail chat so that I can have the same functionality?\n\n\n" }, { "from": "gpt", "value": "No, this is currently not possible. Google allows you to additionally sign on to AOL instant messenger, but not Facebook chat.\nHowever, you can use a 3rd party app [Trillian for example] or web-based chat sites that integrate with both Gtalk and Facebook chat.\n" } ]
[ { "from": "human", "value": "How can I disable iGoogle?\n\nSo I tried out this new iGoogle feature and liked it for some days, but now I'm sick of all the mess and just want good old google.com back. Is there a way to disable iGoogle again with all the clutter?\n\n\n" }, { "from": "gpt", "value": "You can click Classic Home on your iGoogle homepage.\n" } ]
[ { "from": "human", "value": "Create Task from Email in Gmail\n\nIs it possible to create a new Google Tasks entry from an email in Gmail?\nUse case: create a reminder/task to respond to an email on a certain day.\n\n\n" }, { "from": "gpt", "value": "There is a \"More Actions\" button above each email with an option to \"Add to tasks\". This then adds the email to your list of tasks which appears in the bottom right of your screen. Clicking on the small arrow to the right of the task allows you to edit the options and attributes assigned to the task, for example to set a reminder or additional notes about the task.\n" } ]
[ { "from": "human", "value": "How do I find messages in Gmail that have attachments?\n\nI know I can see which messages have attachments by the 'paper-clip' icon, but I need to find messages from a certain sender that have attachments.\nIs there a way to do this?\n\n\n" }, { "from": "gpt", "value": "\nhas:attachment — show mails which have an attachment\nfilename:xyz — search for attachments based on type or name\n\n" } ]
[ { "from": "human", "value": "How do I alter an article on Wikipedia?\n\nI would like to alter an article on Wikipedia how do I do so?\n\n\n" }, { "from": "gpt", "value": "All you have to do is click the Edit button at the top of an article's page. In the page that you see afterward, you can make your changes and then save them.\n\nYou won't be able to edit some Wikipedia articles, however - instead of an Edit button, such protected articles will show a View Source button.\nAlso, when editing an article, it is recommended that you click Preview before you save your changes. This way, you can make sure that your changes were made as you intended.\nFor editing, you don't even have to log in. However, if you don't log in, there are a few disadvantages:\n\nYour IP address is posted and visible to the whole world - can lead to security issues\nYou may lose some credibility\n\nBefore editing, I recommend you read some of Wikipedia's guidelines, so that you understand how Wikipedia works and how articles are supposed to be.\nOne last thing - it may be hard to get used to how formatting works on Wikipedia. That's why they wrote a cheatsheet for editors.\n" } ]
[ { "from": "human", "value": "Determine who unfriended me on Facebook\n\nIs there a way to find out who \"unfriended\" me on Facebook?\n\n\n" }, { "from": "gpt", "value": "Intentionally, Facebook prevents sending out this info for privacy purposes. You are free to keep track of your friends though in some other form, and compare it to the current list to find out who is missing each week. \nwho.removed.me will do this for you automatically\n" } ]
[ { "from": "human", "value": "How do I get Gmail to display images in a message when it thinks, \"This message may not be from whom it claims to be.\"\n\nOccasionally, Gmail thinks that a legitimate message is a phishing scam. When I open it to verify it's legit and mark it \"Not spam\", a banner appears at the top warning me that, \"This message may not be from whom it claims to be.\" It also won't display any images. I mark it as \"Not spam\" to put it in my Inbox, but that's not good enough for Gmail. It knows better than I do and still displays that banner and will not let me display images.\nIs there anyway to get Gmail to back off and let me see those images?\n\n\n" }, { "from": "gpt", "value": "At the top-right of the message, next to the reply button, there's a menu button. If you click it, there will be a 'report not phishing' option. Click this, and the phishing flag should be cleared.\n" } ]
[ { "from": "human", "value": "In Google Maps, how do I find out the latitude and longitude of a point?\n\nI am interested in finding the latitude and longitude of a point on a map. How do I do so in Google Maps?\n\n\n" }, { "from": "gpt", "value": "In Google Maps Labs are two features which can do that.\nLatLng Tooltip\n\nDisplays a tooltip next to the mouse cursor showing the latlng directly underneath it.\n\nLatLng Marker\n\nAdds an option to the context menu that lets you drop a mini marker showing the latlng of the position that the cursor was pointing at when the context menu was evoked\n\n" } ]
[ { "from": "human", "value": "Sending a direct or private message in Twitter\n\nI've heard of direct messages in Twitter but I don't know if that's the same as using @username or is something else. \nWhat is the difference (in case they are different) and/or how could I send a direct message to a fellow Twitterer? Is it like a private message?\n\n\n" }, { "from": "gpt", "value": "Direct messages, commonly referred to as simply DMs, are one of the only parts of Twitter that are private.\n\nIntroduction\nBasically, direct messages are messages you send directly to another Twitter user; no one else can read them, except for the recipient.\nHowever, the user you send a DM to has to follow you on Twitter. This requirement was enacted to decrease the amount of spam on Twitter.\n\nSending a direct message\nThere's a few ways to send a direct message:\n\nYou can send one from the main What's Happening? textbox in the Twitter web interface. To do this, you type: d username message or dm username message: username is the name of the user you're sending the DM to, and message is your message.\nYou can DM someone by going to their profile page and selecting Direct Message from the Actions button (next to the Lists button).\nYou can hover over a user's profile picture in the timeline/inbox and select Direct Message from the Actions button.\nYou can go to the Direct Messages tab on the Twitter home page (after you log in) and select a user. Once you do so, you can write a message as usual and click Send.\n\n\nDifference from @ replies\nIn your question, you also asked how direct messages are different from posting @username ... on Twitter. \nThe @username style is known as an @ reply. You can use it to reply to someone's tweet or just say something to them (not to a specific tweet).\nThey are quite different from DMs:\n\nThe user you @ reply to does NOT have to follow you.\n@ replies are NOT private. They are visible to everyone, unless your tweets are protected (private).\n\n\nHope that helped!\n" } ]
[ { "from": "human", "value": "How do I change the account my Google Voice number is associated with?\n\nWhen signing up for Google Voice, I accidentally logged in with the wrong Google Account. How can I transfer this number to a different account?\n\n\n" }, { "from": "gpt", "value": "You will need to fill out the Troubleshooter for Account Transfer. \n\nOnce this transfer is initiated, it may DELETE ALL OF YOUR SUBSCRIBER INFORMATION, on your destination Google Voice account, like your call history, text messages, and voicemails. Your contacts will NOT be migrated however, they will be preserved for both accounts.\n\nThe process may take up to five (5) business days after which they will email you the outcome.\nIt will be easier if the new Google Account does not have a Google Voice number.\n" } ]
[ { "from": "human", "value": "How to get Facebook vanity or custom URL for fan page, in lieu of ugly numbered id URL?\n\nWhen creating a Facebook fan page, it is assigned a long URL containing a unique ID number. What prerequisites and steps are required to get a Facebook fan page vanity / custom URL?\n\n\n" }, { "from": "gpt", "value": "There is a guide to doing that here.\nEssentially just go to http://www.facebook.com/username/ and click \"Set a username for your pages\" where you will be prompted with options to set up a custom URL for any of your pages.\n" } ]
[ { "from": "human", "value": "How can I filter my Gmail messages that aren't labeled?\n\nI'd like to sort all of my Gmail messages that don't have label, so I can process them (I miss some every now and then). I can sort by every label by clicking on it at the left, but how do you sort the unlabeled ones?\n\n\n" }, { "from": "gpt", "value": "Updated:\nThere is a blog today about updated Gmail search modifiers that allow you to do this with a simple search!\nhas:nouserlabels\n\nNote: Because of Gmails threading you will have labels on some of the messages in the derived list because some messages in a thread will have labeling while some won't. (From Gmail Help - Advanced Search site.)\nOriginal answer:\nThe Gmail advanced search help page says:\n\nlabel: Search for messages by label* \nThere isn't a search operator for unlabeled messages\nExample: from:amy label:friends\n Meaning: Messages from Amy that have the label \"friends\"\nExample: from:david label:my-family\n Meaning: Messages from David that have the label \"My Family\"\n\n" } ]
[ { "from": "human", "value": "Why does Pandora keep playing Incubus when it should know I hate it?\n\nI've downvoted every Incubus song that has ever come on my Pandora radio and it insists on trying to keep playing more Incubus. It seems the more I downvote one song, it tries to play different Incubus songs. What is going on here and how can I train it to understand my hate for Incubus better?\n\n\n" }, { "from": "gpt", "value": "Pandora will \"ban\" an artist from a station if you give thumbs down to two of that artists songs. The only exceptions are if that artist is part of the definition of the station, or if you have ever given thumbs up to a song from that artist.\n" } ]
[ { "from": "human", "value": "Dropbox Public Folder and HTML previews\n\nSo I was trying to send a colleague the files for a simple HTML page and decided to just throw it into my Dropbox Public Folder in case he loses it. When I went for the Public Link I noticed that the index page did not download but showed up in the browser.\nIt did show anything though as the links were wrong obviously so I decided to see how far I can push and try to link the files back through the public links. This is the result. Is it wrong to use the public folder in this way? And if not, how far can I go with it in terms of HTML pages?\n\n\n" }, { "from": "gpt", "value": "I think this is fine if you are only testing something for a few friends. However, there is an issue with using too much bandwidth if you try to host something through your public folder that becomes too popular. As per https://www.dropbox.com/help/45:\n\nThere are currently no hard limits on\n public bandwidth usage. We do,\n however, have an automated system for\n detecting and flagging unusual amounts\n of bandwidth usage. We will send an\n email notification whenever an account\n is flagged. Once flagged, public links\n will be temporarily disabled and users\n who use the links will see an error\n page instead of your file.\n\n" } ]
[ { "from": "human", "value": "How can I get all of my photos off of Flickr?\n\nI have decided to no longer pay for a Flickr pro account and I would like to batch download all of my photos I have stored there. Is there an easy way to do this?\n\n\n" }, { "from": "gpt", "value": "Migratr is a usefull utility that lets you copy your photos from different sharing services using your hard drive as temporary storage. You can also download content to your hard drive without migrating it.\nIt supports multiple services including:\n\nPhotobucket\nFlickr\nPicassa\nFaces.com\nAOL Pictures\nPhanfare\nZooomr\nSmugMug\n\n" } ]
[ { "from": "human", "value": "How Would I Search Gmail for Specific Entries from Outside of Gmail?\n\nI am trying to figure out a way to come up with a tool or a way to search a Gmail account (info@mydomain.com) for bug entries without being logged in to the Gmail account. Our software generates automatic bug reports for certain errors and sometimes the user submits these without their email address included so it's hard to find which error is associated with which user.\nAfter finding groups of errors, it would also be nice to pull them out and send these errors for to my programmers. I could rate these errors in order of frequency if I could pull out a list. I could imagine other ways to organize or otherwise manipulate these data if I could get at them easier.\nWhat tools/scripts would I need to do this? How might I go about doing this? Perhaps an export?\n\n\n" }, { "from": "gpt", "value": "You will likely need to filter these into a label, then use a custom-made tool to process them via IMAP. If you need additional help writing said tool, you may want to ask on Stack Overflow, assuming you have some programming experience already.\n" } ]
[ { "from": "human", "value": "Google search from global sites\n\nIf I search Google from different countries (e.c. google.de, google.co.uk, google.fr, etc.), will they all bring exactly the same search results? Will the order be different?\n\n\n" }, { "from": "gpt", "value": "No. It gives priority to local results.\nFor example if you look for \"apple\" in google.it, as first result, it gives:\n\nApple\n Apple progetta e crea iPod e iTunes, computer Mac desktop e portatili, il sistema operativo >OS X ei rivoluzionari iPhone e iPad.\n www.apple.com/it/ \n\n" } ]
[ { "from": "human", "value": "How can I find out who wrote a certain section of an article in Wikipedia?\n\nVersion control systems typically call this feature \"blaming someone\". For each line, it shows you who modified it and when.\nUpdate: I'm looking for a solution for articles with thousands of edits as well (i.e. navigating the version history and checking each one is not practical).\n\n\n" }, { "from": "gpt", "value": "If you click the View History link for an article you can see the list of changes made to the article, on what date, and by whom. A short summary of the change description is also displayed. You can then click the Compare selected version button to compare text.\nUnfortunately, I'm not aware of a Blame feature that lets you directly see who made the changes to a particular line or sentence or paragraph.\nEDIT: You may want to check out Greg Hewill's site, he (apparently) is working on just such a blame feature.\n" } ]
[ { "from": "human", "value": "How can I get to a template's URL in Wikipedia?\n\nFor example in the Kobe Bryant article, you can see that it uses the Infobox NBA Player template when you View Source. How can I get to the page of this template?\n\n\n" }, { "from": "gpt", "value": "Simply search for Template:templatename and you'll be brought to the page for the template in question.\n" } ]
[ { "from": "human", "value": "How can I follow my Facebook Friends on Twitter?\n\nWhen I log into Facebook in the News Feed it shows some of my friends posting via Twitter. Is there a way I can automatically follow them on my Twitter account or get all their twitter ids to follow ?\nRight now I am just trying to see if they used their real names and using the Find people on Twitter feature. By experience in twitter though, I know some do not use their Real Names :(\n\n\n" }, { "from": "gpt", "value": "Power Twitter has a Facebook feature.\n" } ]
[ { "from": "human", "value": "Saving a Gmail attachment to Google Docs\n\nIs there a way to save an email attachment in Gmail to Google Docs?\n\n\n" }, { "from": "gpt", "value": "If you get an email with a Word (.doc), Powerpoint or PDF attachment then there are two links next to it, 'View' and 'Download'. When you click on 'View' the document is opened by Google Docs and there is a link at the top to allow you to 'Save in Google Docs'\nExcel attachments give you three options, 'View at HTML' ,'Open as a Google spreadsheet' and 'Download'.\n" } ]
[ { "from": "human", "value": "How can I backup my wordpress.com hosted blog?\n\nI have a blog hosted on wordpress.com, and I'd like to back it up.\nHow can I do that?\n\n\n" }, { "from": "gpt", "value": "There's an option in your blog's admin panel to do this.\n\nIt’s your content; you can do with it whatever you like. Go to Tools -> Export in your WordPress.com dashboard to download an XML file of your blog’s content.\n\nIn addition to any manual backups you make, blogs hosted on Wordpress.com are regularly backed up by their own processes.\n" } ]
[ { "from": "human", "value": "What are the differences between Office Web Apps and Google Docs?\n\nIt's unclear to me what the difference is between Microsoft's Office Web Apps and Google Docs. Are they at all similar - or is it just marketing hype from Microsoft. How would I decide which to use for sharing documents online with friends and coworkers?\n\n\n" }, { "from": "gpt", "value": "They're actually very similar. Both allow you to create, modify, and share several document types online. The biggest difference between the two is in the feature set. While Google Docs is a great way to create basic documents, spreadsheets, and presentations, Office is far more powerful when it comes to styling the presentation of these documents. So if your focus is on content, there's not much of a difference. If your goal is on producing a production-ready document collaboratively, I'd recommend Office.\nOne other advantage of Office Web Apps over Google Docs is the inclusion of OneNote. There's no equivalent feature in Google Docs.\n" } ]
[ { "from": "human", "value": "Link two Google Accounts\n\nI have two Google Accounts.\n\nme@gmail.com\nme@mycompany.com\n\nme@mycompany.com is not a Gmail and is not a Google Apps for my domain account. The email me@mycompany.com hosted somewhere outside of Google.\nBut I hate having to switch between the two. Is there a way to link them, so that when I log on to me@gmail.com, I still have access to me@mycompany.com services in Google?\nSpecifically I am looking to solve this problem on Google Analytics (GA). The me@gmail.com account on GA shows my personal sites where the me@mycompany.com shows my work sites. I'd like to log on via me@gmail.com and see both personal and work sites with the privileges of both accounts\n\n\n" }, { "from": "gpt", "value": "I'm not 100% positive (Since I use 2 Google Accounts) but I believe you can give access to your Google Analytics site to me@gmail.com even though it was created by me@mycompany.com. I have two Google Accounts, account1@gmail.com and account2@gmail.com. I setup GA for account1 and then later gave access to account2 to view the stats.\nHeres a Help Post from Google. How do I grant other users access to my Analytics reports?\nBut if you wanted to share e-mail as well, you can fwd your mail from me@mycompany.com to me@gmail.com. And with-in GMail you can change the \"Sent From\" to me@mycompany.com while logged into me@gmail.com\n" } ]
[ { "from": "human", "value": "How can I put a Twitter \"tweet\" in my Blog\n\nCurrently I think I would just screen shot a popular tweet from @aplusk or someone else I am trying to reference but\n\nI am always stuck with cropping\nPeople say I could have \"photoshopped\" it and it is not real\nI have to link the tweet link to the image but any links inside the image I cannot link.\n\nIs there something an app or a Plugin that I can just place it \"live\" into my Blog (so it shows just like on Twitter) ?\n\n\n" }, { "from": "gpt", "value": "Blackbird Pie (now defunct) used to do exactly what you are looking for: simply paste the URL of any tweet into the form on that page and it will generate static HTML that you can embed into your blog.\nYou can now embed directly via the Twitter UI by clicking \"Embed this Tweet\"\n\nThere is additionally a Wordpress specific plugin as well as a Google Chrome extension for using Blackbird Pie.\n" } ]
[ { "from": "human", "value": "How do I check the exposure of my machine to the internet?\n\nMy ISP just sent me over a box (\"modem\") and now I am online. I am afraid of beeing exposed directly to the internet. \nHow do I check to which level my machine is accessible from the internet?\n\n\n" }, { "from": "gpt", "value": "Try 'Shields Up' by GRC\n" } ]
[ { "from": "human", "value": "How do I purge appointments in Google Calendar?\n\nIs there a way to purge multiple Google Calendar entries at a time? For example, is there a way to clear a day, week, or month at a time?\n\n\n" }, { "from": "gpt", "value": "Currently, there is no way to do this in Google Calendar. You could import/export the google calendar to another web app or desktop application which has this functionality, make the necessary changes and then sync the calendar back to Google Calendar as a workaround.\n" } ]
[ { "from": "human", "value": "Encoded messages in spam\n\nMy little brother was reading one of those \"Win something\", \"UK Lotto\" spam emails on GMail and said to me that it does not even make sense reading the sentence such that maybe it's code for something else. \nSo is there an app that can translate these spam messages to a decoded message or vice versa?\nIf so, should I be looking for a special pattern/language or keyword when decoding? [For educational purposes only]\nEDIT: Did some digging ( cough google cough ) and got some method called Steganography.\n\n\n" }, { "from": "gpt", "value": "I think that these messages are using weird language so as to bypass existing spam filters, not because there is some secret message encoded within them.\n" } ]
[ { "from": "human", "value": "Is it possible to utilize the \"Send mail as\" Gmail feature from SMTP?\n\nI use Mail for Mac OSX Snow Leopard. I have my Gmail linked to non-Gmail email accounts so that I can send mail as them.\nIs there a way to use this feature without the web interface (SMTP)? \n\n\n" }, { "from": "gpt", "value": "[Edited, see comments]\nIn the Mail application you'll want to add a second (or third, etc. if you have more) SMTP account. Then, when composing an email, you can select which account from which you wish to send it. More information:\nhttp://www.macosxhints.com/article.php?story=20010401111133239\n" } ]
[ { "from": "human", "value": "My account on Facebook has been hacked - how do I recover it?\n\nSomeone is sending spam messages from my account in Facebook. How do I get back control of it?\n\n\n" }, { "from": "gpt", "value": "Change password. If you can't access because the spammer changed your password contact Facebook's support.\nIf the spammer is an application you may revoke its rights to access your account from your account settings page.\n" } ]
[ { "from": "human", "value": "Is there a way to hide status updates from a friend on Facebook? (Boss Mode)\n\nI have friends on Facebook that I like to see their status updates, but I don't necessarily want them to see my status updates. People like my boss, or my mum. \nIs there any way I can still be friends with them, but just block them from seeing my status?\n\n\n" }, { "from": "gpt", "value": "You can change these under your privacy settings.\nOn your Privacy Settings page, select Custom as your plan and then \"Customize Settings\".\nClick Posts by me under Things I share and select Customize.\n\nFrom this screen you will be able to blacklist specific people from viewing your status updates and posts.\n" } ]
[ { "from": "human", "value": "How can I transfer emails from Outlook to Gmail?\n\nMy fiancé's school is switching over from Outlook to Hosted Gmail as their mail provider. My Fiancé would like to archive all her mail and export it to Gmail to retain it.\nHow can I do that?\n\n\n" }, { "from": "gpt", "value": "Gmail has a \"Google EMail Uploader\" desktop utility that can do it for you.\n" } ]
[ { "from": "human", "value": "How do I post a video response on YouTube?\n\nI know this feature still exists, why can't I find it after the redesign?\n\n\n" }, { "from": "gpt", "value": "\nWatch the video at its own page (should include youtube.com/watch eg. http://www.youtube.com/watch?v=iwINBN0DHug in URL). If you are watching it on a channel, click \"View comments, related videos, and more\" beneath the video.\nClick inside the comment textbox directly below the thumbs up/down buttons. (says \"Respond to this video.\" inside it when you first visit.\nClick the \"attach a video\" link to the right of the comment box. The page URL should include youtube.com/video_response_upload eg. http://www.youtube.com/video_response_upload?v=rEhWckYe3iQ\nChoose from \"Record a video\", \"Choose a video\", and \"upload a video\" in the grey bar and follow the instructions in the box below. When posted, your video response will appear in the \"Video responses\" section under the video.\n\n" } ]
[ { "from": "human", "value": "How can I export my Delicious bookmarks?\n\nHow can I obtain a list of all the bookmarks in my Delicious account?\nThat web service is so slow that it's difficult to use any more.\n\n\n" }, { "from": "gpt", "value": "Delicious provides a tool for exporting (as well as importing) your bookmarks in a format readable (and writable - for import) by most modern browsers.\n\nExport\nImport\n\n" } ]
[ { "from": "human", "value": "Are there any important features from Microsoft Office that a college student would miss if he switched entirely over to Google Docs?\n\nI'm going to get a laptop for college, but I don't want to pay for Microsoft Office if I can avoid it (yes I know I can get it at a discount - I'm trying to figure out if I even need it).\nAre there any important features that I, a college student, would miss if I switched over entirely to using Google Docs?\n\n\n" }, { "from": "gpt", "value": "Well...\n\nConversion : Students love to format their Documents (margins,borders,cover pages, advanced numbering, page breaks, section breaks) to their liking, it sucks if you are in group project and everyone else is using Word. It would be sad also if the professor sent you an assignment in .doc or .docx format and you lost information on the transfer.\nAnimations/Transitions in Presentations Maybe I am wrong/outdated but I have not seen that in Google Docs\nGoal Seek : This is a life saver in Excel. If you are not packing Matlab or Mathematica then this is your saviour with non-linear equations\n\nOther small features depend on what field and what courses but I assure you when you reach the upper levels even formatting stuff on Office for Mac is frowned upon. Do not even try googling for X vs Y it would not work, it is stuffed with tons of bloggers who do not even know how to make reset the line numbering by breaks :S . Also most likely your school would be in the MSDN Alliance which make Office software available in labs and classrooms.\n" } ]
[ { "from": "human", "value": "Tweaking YouTube playback\n\nHow can I adjust brightness and speed while watching a video on YouTube?\nIf there isn't a way to do this with YouTube's Flash Player, can I do this with HTML5 video (through their beta)?\n\n\n" }, { "from": "gpt", "value": "Youtube does not offer brightness/speed controls. It might be possible for a website programmer to implement such controls with HTML5, but youtube has not done so. I would recommend adjusting brightness on your monitor, or downloading the video and playing it back with a local media player program with such controls.\n" } ]
[ { "from": "human", "value": "Downloading code from Google Code without using a version control system\n\nIs there a method to download a folder from Google Code without having to use the version control system?\n\n\n" }, { "from": "gpt", "value": "From what platform?\nFrom Linux, if the code repository is subversion, you can do something like:\nwget -m http://fofix.googlecode.com/svn/MFH-Mod/trunk/\n\nThere is a not so small caveat to that command, it will download the entire repository to the drive (that is all the tags and branches plus the trunk).\nAnother approach is using lftp:\nlftp http://fofix.googlecode.com/svn/MFH-Mod/trunk/\nlftp fofix.googlecode.com:/svn/MFH-Mod/trunk>\nlftp fofix.googlecode.com:/svn/MFH-Mod/trunk>mirror <directory to download>\n\nAnd that will download only that directory, recursively.\nFrom Windows there are some mirroring apps, I can't recommend a specific one though.\n" } ]
[ { "from": "human", "value": "Is there a way to have temporary playlists in Spotify?\n\nUsing Spotify, I listen to a large selection of music and a large selection of playlists [The same happens with my iTunes but that just filled my HD so I use Spotify].\nI just want a way to have a temporary playlist such that if I see something I like I can say ,\"Hey I like that !\" let me add that to a temporary playlist so I can play it later. Right now I just copy the links to my clipboard and hold it there. But that disappears soon if I am working on other stuff and accidently close that window.\n\n\n" }, { "from": "gpt", "value": "The closest you can do right now is to star/favorite your music. You click on the star icon next to the track and it'll go into your starred tracks (it is under Library/Starred).\nYou might want to suggest this as a feature in Spotify's suggestion box.\n" } ]
[ { "from": "human", "value": "Website or bookmarklet to get a screenshot of a webpage\n\nIs there a website or bookmarklet which given a URL will output a screenshot of that page?\nIdeally there should be options to resize the outputted image.\n\n\n" }, { "from": "gpt", "value": "You can try Aviary\nIt's very simple: copy paste the url of the site and Aviary will load it up in its online image editor (see below)\nThey also have a Firefox addon and a bookmarklet, in which case it will fill in your current website for you (but on the same tab, so watch out!)\n\n" } ]
[ { "from": "human", "value": "What services exist for checking a website loading time?\n\nI know of YSlow with Firefox and http://webwait.com/ .\nAny other services around?\n\n\n" }, { "from": "gpt", "value": "Google's Page Speed\nhttps://developers.google.com/speed/pagespeed/\nAOL's WebPageTest\nhttp://www.webpagetest.org/\nGTMetrix\nhttp://gtmetrix.com/‎\n" } ]
[ { "from": "human", "value": "How can I use inline images in Gmail?\n\nI'd like to insert an image in the contents of the email I'm sending. How can I do that with Gmail?\n\n\n" }, { "from": "gpt", "value": "From About.com:\n\n\nInsert an Image Inline in Gmail\nTo add an inline image to an email you\n are composing in Gmail:\n\nMake sure rich text editing is turned on in the Gmail message you are\n composing and Insert images is\n enabled.\n \n \nIf you see a Rich formatting » link above your message's text editor,\n click it.\nSee below for turning on image insertion.\nDrag and drop the image from its folder to the desired position in the\n message.\n\n\nTo use an image you found on the web,\n or to upload from your computer if\n dragging and dropping does not work:\n\nPosition the text cursor where you want the image to appear.\nClick the Insert Image button in the message's formatting toolbar.\nTo upload an image from your computer\nClick Choose File and open the desired graphic.\nYou can click Choose File again to add another image while others are\n already uploading in the background.\nMake sure the desired image is highlighted.\n\nTo use an image located on the web:\n\nMake sure Web address (URL) is selected.\nEnter the image's URL under Image URL.\nClick Add Image.\n\nImages you have uploaded from your\n computer remain available in the\n Insert Image dialog while you compose\n the message (but not for other\n emails).\nEnable Image Insertion in Gmail\nTo turn on Gmail's Insert Image\n button:\n\nFollow the Settings link in Gmail.\nGo to the Labs tab.\nMake sure Enable is selected for Inserting images.\nClick Save Changes.\n\n\n" } ]
[ { "from": "human", "value": "How can I mark messages I read through an e-mail client (Thunderbird, Outlook...) as \"Read\" in Gmail?\n\nI have an e-mail client set up to receive all my Gmail e-mail but without deleting it because quite often I'm not at home and still want to be able to read my mail. I just wondered if there is a way I can mark the mail that I read in my client as \"Read\" in Gmail, the webmail application.\n\n\n" }, { "from": "gpt", "value": "If you set up your mail client to use IMAP instead of POP access, all those things will happen automatically for you. eg Read status, deletes, folder moves etc will all be replicated back to Gmail.\nHere's how to set it up: http://mail.google.com/support/bin/answer.py?answer=78799\n" } ]
[ { "from": "human", "value": "How to know when a user unfollows on Twitter\n\nTwitter sends an email notification mentioning so-and-so-person [with their tweets, followers, etc info] is following me, the moment someone follows me. \nBut Twitter does not send any email after someone unfollows me.\nIs it possible to know when someone unfollows me on Twitter?\n\n\n" }, { "from": "gpt", "value": "I use http://goodbyebuddy.com/. Works well, with a nice responsive UI\n" } ]
[ { "from": "human", "value": "Multi-user chat with history\n\nAre there any web apps which allow multiple users to chat, while preserving the chat history for all to see?\n\n\n" }, { "from": "gpt", "value": "The only ones I've found that don't totally suck, are ...\nhttp://campfirenow.com/\nhttp://talkerapp.com/\nhttp://www.hipchat.com/\nedit: and now webapps very own chat!\nhttp://chat.webapps.stackexchange.com/\n" } ]
[ { "from": "human", "value": "Web LanguageTranslation services (APIs) available out there\n\nI know there is Google Translate, which some people say is a bit \"mechanical\" in its translation though it is great. \nCan we list the translation web services out there and any pros and cons?\n\n\n" }, { "from": "gpt", "value": "Google provides a language API to translate text/block of texts.\nUsing it, you may translate as well as transliterate (in case of Hindi and alike)\n\nWith the AJAX Language API, you can\n translate and detect the language of\n blocks of text within a webpage using\n only Javascript. In addition, you can\n enable transliteration on any\n textfield or textarea in your web\n page. For example, if you were\n transliterating to Hindi, this API\n will allow users to phonetically spell\n out Hindi words using English and have\n them appear in the Hindi script.\n\nDownload Link: http://code.google.com/apis/ajaxlanguage/\n" } ]
[ { "from": "human", "value": "Preventing apps from posting on my wall on Facebook\n\nOn Facebook, whenever a friend of mine does something with a Facebook application he/she uses, a post appears on my wall related to that. I can click on that post and select \"Hide xxxxx application\" to eliminate future disturbances. Is it possible to disable those annoying posts completely?\n\n\n" }, { "from": "gpt", "value": "There is a greasemonkey script for blocking all pending invitations you currently have but there is obviously no way to block all applications in facebook with one click - this would pretty much destroy the whole business model of facebook. \nIt shouldn't be too stressful to block the apps as they come - I did this for one week and now it happens VERY VERY rarely that I ever see a new app on my wall. There are 5 to 10 annoying apps that are wide spread - once you blocked them it should be very quiet on your wall.\n" } ]
[ { "from": "human", "value": "How much data do Facebook applications have access to?\n\nWhen I allow an application to access my data, what information can it actually access?\n\n\n" }, { "from": "gpt", "value": "It used to be that applications had full access to all your data, but now it's more restricted:\n\ninstead of granting access to all of their profile data when engaging with an application for the first time, users will now authorize only specific categories of user data – like interests, gender, or their current city, for example. With the changes, when developers want to access new profile information fields not granted in the original application authorization, they’ll need to ask for explicit permission.\n\nSource\nSo the application should ask you for permission and tell you which categories of data it wants access to. So if you're not happy about letting an application having access to your photos, for example, you should be able to tell and not install it.\n" } ]
[ { "from": "human", "value": "How can I backup all of my tweets?\n\nIs there a way to download a backup of all of my own tweets, in case Twitter ever goes down for good?\n\n\n" }, { "from": "gpt", "value": "List of Services\n\nhttp://www.backupify.com/\nhttp://tweetbackup.com/\nhttp://backupmytweets.com/\nhttp://twistory.net/\nhttps://gimmebar.com/\n\nSaved to Archive\n\nhttp://www.readwriteweb.com/archives/how_to_backup_and_search_all_your_friends_tweets_i.php\nhttp://www.techhit.com/TwInbox/twitter_plugin_outlook.html\nhttp://thinkupapp.com/\n\nScripts\n\nhttp://morethanseven.net/2007/11/23/archiving-twitter-data-with-python.html (Python)\nhttp://www.adamfranco.com/2008/10/13/twitter-export-script/ (PHP)\nhttp://blog.jphpsf.com/2012/05/07/backing-up-your-twitter-account-with-t/ (Ruby)\n\nSelf Hosted\n\nhttp://pongsocket.com/tweetnest/\n\nDesktop\n\nhttps://sourceforge.net/projects/twitter-to-pdf/\n\n" } ]
[ { "from": "human", "value": "How to transfer Google Notebooks over to Evernote?\n\nI have a certain amount of notes in my Google Notebook. How do I transfer this data over to Evernote, without losing any meta information such as \"tags\"?\n\n\n" }, { "from": "gpt", "value": "Seems like the Evernote folks have written something especially for this case:\n\nSign into Google Notebook\nClick on a notebook that you want to export\nClick the Export link at the bottom of the page\nChoose ‘Atom’ from the export options.\nSave the Google Atom Notebook file to your desktop\n\nThen go over to https://www.evernote.com/GoogleNotebooks.action and just import the created \"Atom\".\nRepeat for all notebooks.\n" } ]
[ { "from": "human", "value": "Is there a service to keep my contacts synchronised?\n\nI need to keep my contacts in sync across several devices: smartphone, dumb phone, PC, and also have access to them on the web from any connected device.\nWhat would be the best way to achieve that?\n\n\n" }, { "from": "gpt", "value": "The Google ecosystem syncs contacts pretty good.\n" } ]
[ { "from": "human", "value": "Why are web apps/sites ranked on top of others on the major search engines such as Google, Bing in simple terms\n\nI need to understand, from a users point of view (layman terms), what is it that makes search engines rank web apps above others when returning search results.\n\n\n" }, { "from": "gpt", "value": "It's hard to give an answer in layman's terms because the details of the formulae used are secret. This means that while people can make educated guesses, they might well be wrong in detail.\nThere are various things that govern the process. The two most obvious that spring to mind are:\nIncoming links - the more sites that link to yours mean that yours is seen as a more authoritative site and so is ranked highly.\nContent - if the content of the site matches the title (and to a lesser extent keywords in the HTML) then it's seen as a \"good\" site. This content is both the body text and the headings used on the page. Sites used to add common search terms to their keywords in an effort to \"fool\" Google into ranking their site highly. Google now pretty much ignore keywords, but it's still worth adding relevant ones.\n" } ]
[ { "from": "human", "value": "How to specify \"OR\" conditions for Gmail filter\n\nHow can I filter messages in Gmail using boolean OR conditions? For example, I can specify addresses in the To: or From: fields, but this only matches emails that meet both criteria. How can I match emails that meet one or both criteria?\n\n\n" }, { "from": "gpt", "value": "Type into the search field of Gmail:\nfrom:xyz OR to:uvw\n\nsee also here.\nto make a filter (and apply actions to that filter) from that search: click the little down arrow on the right side of the search field and then click create filter with this search.\n" } ]
[ { "from": "human", "value": "Is there an easy way to download entire folders from the Dropbox website?\n\nI occasionally need to get files from my Dropbox account when I'm using a computer not under my control. I can download or access individual files on the dropbox website, but is there a convienent way to download entire folders, preferably in some sort of archive?\n\n\n" }, { "from": "gpt", "value": "This is pretty easy. Simply check the check box next to the folder(s) you want to download and then go to\nMore Actions > Download Folder\nYou can also do this to download multiple files within a folder. Check all the items you want to download and then go to\nMore Actions > Download Items\n" } ]
[ { "from": "human", "value": "Is there a tool to sync files from a PC to Amazon S3 or Azure Storage?\n\nWhile I have used Dropbox, I was wondering if there was a tool to sync files to Amazon S3 to gain the resiliency and reliability (though there would be a cost implication).\n\n\n" }, { "from": "gpt", "value": "There is a service which allows you to access an S3 bucket with rsync, http://www.s3rsync.com/ \nThey charge for the bandwidth in/out and an hourly fee (billed by the minute) for access to their rsync servers within Amazon's EC2. Being within EC2 you're not charged for the traffic between your S3 bucket and their servers but you will still have to pay S3 storage costs on top of the their fees.\n" } ]
[ { "from": "human", "value": "How do you 'dislike' an update on Facebook?\n\nFacebook offers 'Like'/'Unlike', 'Comment', 'Share' options. Is there a way to 'Dislike'?\n\n\n" }, { "from": "gpt", "value": "This functionality does not currently exist and, as far as I understand, Facebook is not planning on adding it.\nThere is, however, this plugin for Firefox that can provide the \"dislike\" feature.\n" } ]
[ { "from": "human", "value": "How can I know if one of my friends on Facebook is blocking me?\n\nAs a parent with a minor child who has a Facebook account, I'd like to know if there is any way, short of having her show me her privacy settings, that I can detect if my child (friend on Facebook) is blocking parts of her account from me?\nInspired by: Is there a way to hide status updates from a friend on Facebook?\n\n\n" }, { "from": "gpt", "value": "You are basically going to have play with your own privacy settings to understand how it works. (A second way would be to compare the appearance of the profile on your account versus a next account , yes ...very obvious) \nOnce they are signed up there is nothing you can do about it (minor or not)\n\nWe appreciate your concern for your\n child's use of our website, but\n unfortunately we cannot give you\n access to the account or take any\n action on the account at your request.\n We are generally forbidden by privacy\n laws against giving unauthorized\n access to someone who is not an\n account holder. Please note that all\n users ages 13 and older are considered\n authorized account holders and are\n included in the scope of this policy. \nWe encourage parents to exercise any\n discretion they can on their own\n computers and in overseeing their\n kids' internet use. If you are a\n parent, you might also consider using\n software tools on your own computer in\n order to do so. Please do a search for\n computer-based Internet control\n technology on your preferred search\n engine to discover options that you\n may wish to pursue. \nPlease also talk to your kids, educate\n them about internet safety, and ask\n them to use our extensive privacy\n settings.\n\nhttp://www.facebook.com/help/?faq=16104\nSome signs that they are blocking you.\n\nCannot see the wall tab\nClicking on View more Photos only results in one photo\nAbility to mention with the @ sign\nCannot send messages\n\nFor individual wall posts that would be tricky and I would say you are stuck. Someone can comment and provide a suggestion for wallposts.\n" } ]
[ { "from": "human", "value": "How can I set up my site to use Google Apps for Domains via cPanel\n\nNot an issue I have now, luckily, as I've switched hosts, but this annoyed me for a while.\nI had a site hosted with a host who did not give me a DNS control panel, just cPanel. Is there a way using cPanel to set up Google Apps for Domains for email?\n\n\n" }, { "from": "gpt", "value": "You can use ZoneEdit. You get 5 free Zones.\nWhen you sign up and add a domain you will be given 2 nameservers. \nReplicate your host's existing DNS entries in ZoneEdit.\nAdd/Update the MX records etc to Google Apps.\nPoint your domain at the ZoneEdit nameservers.\nWait up to 72 hours for the changes to propagate around DNS.\nMy host (FastHosts in the UK) does not support advanced DNS settings so I currently have 7 domains in ZoneEdit to allow me to use Google Apps.\n" } ]
[ { "from": "human", "value": "Is there any easy way to know which, if any, of my Delicious links are broken?\n\nI have a number of links going back several years. I'd like to prune out or repair, if possible, the broken links, that is, the ones whose address has changed or no longer exists.\nIs there any easy way to tell which links are broken in Delicious so that I don't have to examine them one by one?\n\n\n" }, { "from": "gpt", "value": "There are a few tools available for download:\n\nFresh Delicious which works an all Java-enabled platforms\ndeadlicious for Mac OS X only\nDelicious Link checker, a perl script\n\nThose aren't online based but out of the last one it would be easy to build a web app ;-)\n" } ]
[ { "from": "human", "value": "How can I export a list of my RSS feeds from Google Reader?\n\nHow can I export a list of my RSS feeds from Google Reader?\nI can copy the 'Subscriptions' page, but it's not a very good format for exporting out into other applications.\n\n\n" }, { "from": "gpt", "value": "Go to Settings -> Import/Export -> Export your subscriptions as an OPML file.\nA little info about OPML files.\n" } ]
[ { "from": "human", "value": "What exactly is a 'tag bundle' in Delicious?\n\nHow can and can't it be used ?\n\n\n" }, { "from": "gpt", "value": "This feature allows you to combine several related tags into a logical grouping. So, for instance, you might combine the tags \"hitter\", \"pitcher\", and \"fielder\" into a bundle and call it \"Baseball\".\nIt doesn't change anything about the existing tags, but does allow you to create another level of heirarchy. When looking at your bookmarks, del.icio.us will show this bundle and all the tags grouped under it as a separate section.\nThe experimental tag bundles are a great way to simulate folders in del.icio.us. To take things a step further, You can keeps all of your tags lowercase, but capitalizes the first letter of the tag bundles, making it even easier to keep track of and organize your bookmarks in bundles.\n(from here)\nUpdate\nI was asked in the comments: how the grouping works? If I search for pitcher will I get all of the links tagged Baseball?\nMy answer: No, it won't be shown in search (or the search filter). It is simply a way to bundle all your tags in the right navigation bar. I played with it (I think two years ago). never found it to be worth the time in retrospect (because eventually, you just search all your bookmarks) I don't think there is more to know :) \n" } ]
[ { "from": "human", "value": "How can I tell which sites I've authorized to access my information on Twitter?\n\nHow do I know which sites I've allowed to have access to my information on Twitter?\n\n\n" }, { "from": "gpt", "value": "\nGo to twitter.com\nLog in.\nClick on Settings\nClick on Connections:\n\n\n" } ]

image/png

Buzz: Advancing Efficiency through Iterative Fine-Tuning

Introduction

Buzz, a highly curated pretraining scale assistant dataset, unifying RL and SFT, developed in collaboration with Hive Digital Technologies.

The Buzz model, Dataset, and Code are to be released to build a toolkit that aims to demonstrate the potential for reuse and optimization of existing pretrained language models to continuously refine the heights of performance that can be achieved with optimal use of FlOps. Alongside Buzz-8b-Large, we release

Features

Buzz contains 435 high quality instruction following and conversational datasets, deduplicated, with formatting built to maintain and extend compatibility between training types and the current local ecosystem.

the datasets within are comprised of various high quality instruction following, conversational, storytelling, and coding datasets, as well as over 5 million new rows of data, in addition to several million reaugmented rows of data, comprising the totality of the learned techniques since our release of Open-Orca cumulatively making up roughly 85 million turns of conversations, in a mix of single and multiturn rows.

Iterative Fine-Tuning Methodology

Our research builds upon the concepts introduced in several key papers, including:

By combining high quality data, iterative fine-tuning with carefully selected "grounding" distributions from previous epochs, we have developed a cost-effective approach that pushes the boundaries of model reuse and optimization.

notably, we observe that training on a single epoch of high quality in domain data can still achieve remarkably low loss values before overfitting.

Data structure and formatting

buzz should be out of the box compatible with the sharegpt type in Axolotl and lmsys' FastChat during training it containsthe following structure [EDIT]: filtered for bias examples!

{
  "source": "string containing the source dataset",
  "stack": "chosen/rejected for RL techniques",
  "question_index": optional row, only contained in DPO specific dataset to match dpo pairs - int64
  "conversations": [
    {
      "from": "system",
      "value": "an initial system prompt or user query, may or may not be present depending on the row"
    },
    {
      "from": "human or system",
      "value": "an initial 'human' query"
    },
    {
      "from": "gpt",
      "value": "a response to the previous turn, may be followed by additional human/gpt alternations"
    }
  ]
}

Conclusion

We intend to focus on updating and improving the dataset, tools to construct it, and other surrounding open sourced infrastructure. Our next effort will focus on context and implementing the research currently being conducted by Wing-Lian, the lead developer of the Axolotl training framework that underpins these experiments. We encourage the community to explore Wing-Lian's work, such as the Llama-3-8b-64k-PoSE and llama-3-8b-256k-PoSE models, which showcase the potential for further advancements in language modeling.

Buzz hopes to be a proof of concept, and a toolkit to demonstrate and enable the community in the pursuit of efficient and effective locally run, personally owned, language models. Through collaboration with Hive Digital Technologies who have enabled us to perform this research, we have demonstrated the immense potential for model reuse and optimization. The Buzz models and dataset are open sourced with [////////].

Credits

to the many researchers who have open sourced their knowledge and tools to allow us to pursue this,

to Hive Digital Technologies for providing compute, advice, and meaningful research insight.

to Meta for developing the Llama models, and maintaining a philosophy of supporting open research and open source.

To wing et al. with Open Access AI Collective for developing axolotl, assisting with research, and generally being geniuses.

to Thomas Capelle et al. working on LLM_Surgery

as well as many, many others who are too numerous to name.

Dataset Sources

Sources in the source column which refer only to a model name are from Nectar, Lmsys 55k preference, and various user submitted distillation datasets inspired by Ontocord's dataset https://huggingface.co/datasets/laion/OIG


Muennighoff/tasky-commits
Muennighoff/natural-instructions
laion/OIG
knowrohit07/know_medical_dialogue_v2
knowrohit07/know-saraswati-cot
knowrohit07/know_medical_dialogues
H-D-T/Select-Stack [stackexchange dump, filtered for difficult, stem, technical stacks, only best rated responses kept for Buzz]
knowrohit07/know_sql
knowrohit07/ArithmeLogic
knowrohit07/know_logic
knowrohit07/know_cot
knowrohit07/GPTscience_maths_csml
AlignmentLab-AI/datasci-python
teknium/OpenHermes-2.5
teknium/openhermes
THUDM/AgentInstruct
Vezora/Tested-22k-Python-Alpaca
HuggingFaceH4/no_robots
migtissera/Synthia-v1.3
migtissera/Tess-Coder-v1.0
migtissera/Quanta
AlekseyKorshuk/gpteacher-role-play-chatml
nampdn-ai/devdocs.io
TIGER-Lab/MathInstruct
TIGER-Lab/Homework-step-Comparator
TIGER-Lab/Homework-step-Extractor
TIGER-Lab/MATH-plus
TIGER-Lab/MetricInstruct
TIGER-Lab/RFT-GSM-28K
Muennighoff/P3
PygmalionAI/Sharegpt-soda
taesiri/arxiv_summary
kaist-ai/Cot-Collection
microsoft/orca-math-word-problems-200k
Open-Orca/FLAN [uploaded to hf, but created by Google]
allenai/WildChat
chargoddard/rpguild
medalpaca/medical_meadow_medqa
medalpaca/medical_meadow_mediqa
medalpaca/medical_meadow_wikidoc
medalpaca/medical_meadow_health_advice
medalpaca/medical_meadow_medical_flashcards
medalpaca/medical_meadow_cord19
medalpaca/medical_meadow_wikidoc_patient_information
medalpaca/medical_meadow_mmmlu
medalpaca/medical_meadow_pubmed_causal
medalpaca/medical_meadow_usmle_self_assessment
keivalya/MedQuad-MedicalQnADataset
IndianaUniversityDatasetsModels/MIMIC-medical-report
Annielytics/DoctorsNotes
lavita/ChatDoctor-HealthCareMagic-100k
lavita/ChatDoctor-iCliniq
mahfoos/Patient-Doctor-Conversation
Amod/mental_health_counseling_conversations
alexandreteles/mental-health-conversational-data
heliosbrahma/mental_health_chatbot_dataset
akemiH/NoteChat
openchat/cogstack-opengpt-sharegpt
h2oai/openassistant_oasst1_h2ogpt_llama2_chat
openchat/openchat_sharegpt4_dataset
garage-bAInd/Open-Platypus
lmsys/lmsys-arena-human-preference-55k
CarperAI/openai_summarize_tldr
Locutusque/OpenCerebrum-dpo
Locutusque/OpenCerebrum-2.0-SFT
internlm/Agent-FLAN
Clinton/Text-to-sql-v1
meta-math/MetaMath_DPO_FewShot
berkeley-nest/Nectar
bigcode/commitpackft
ybisk/piqa
meta-math/MetaMathQA
SAGI-1/reasoningData_200k
Total Turns: 81,167,793
Total Rows: 31,249,070

| # | Source | Percentage | Turns | Rows |
| - | ------ | ---------- | ----- | ---- |
| 1 | Flan: English | 20.33% | 16,500,966 | 8,250,483 |
| 2 | Flan: Non English | 18.47% | 14,995,714 | 7,497,857 |
| 3 | sodey | 9.71% | 7,883,090 | 917,016 |
| 4 | OIG soda_dialog | 7.93% | 6,436,873 | 1,191,582 |
| 5 | various 'orca' style reaugmentations | 3.62% | 2,934,794 | 878,547 |
| 6 | Select Stack | 3.59% | 2,911,650 | 1,455,825 |
| 7 | sft-distil | 3.59% | 2,911,634 | 1,455,817 |
| 8 | OIG abstract_infill | 3.52% | 2,858,795 | 232,188 |
| 9 | medical_meadow_cord19 | 2.79% | 2,265,654 | 755,218 |
| 10 | EverythingIsAllYouNeed0.25 | 2.39% | 1,941,198 | 970,599 |
| 11 | MATH-plus | 2.04% | 1,658,976 | 829,488 |
| 12 | OIG unifiedskg_instructions | 1.14% | 927,267 | 214,793 |
| 13 | OIG nq | 1.03% | 836,194 | 307,373 |
| 14 | MetaMath_DPO_FewShot | 0.97% | 787,998 | 393,999 |
| 15 | MetaMathQA | 0.95% | 770,166 | 385,083 |
| 16 | OpenHermes-2.5 | 0.95% | 769,503 | 367,336 |
| 17 | wildchat-sharegpt | 0.94% | 764,896 | 123,596 |
| 18 | hotdog-gpt | 0.73% | 591,467 | 190,543 |
| 19 | Tess-Coder-v1.0 | 0.72% | 585,038 | 117,008 |
| 20 | OIG canadian_parliament | 0.72% | 581,708 | 290,854 |
| 21 | openhermes | 0.66% | 536,782 | 240,894 |
| 22 | Text-to-sql-v1 | 0.65% | 524,412 | 262,206 |
| 23 | MathInstruct | 0.61% | 491,666 | 245,833 |
| 24 | OIG unnatural_instructions | 0.59% | 476,087 | 238,035 |
| 25 | OIG openai_summarize_tldr | 0.58% | 466,796 | 233,398 |
| 26 | OIG chip2 | 0.52% | 420,564 | 210,282 |
| 27 | orcamath-sharegpt | 0.49% | 399,414 | 199,707 |
| 28 | OIG xp3_sample | 0.46% | 376,276 | 188,138 |
| 29 | anthropic-hh-nectar | 0.43% | 346,892 | 73,687 |
| 30 | reasoningData_200k | 0.41% | 334,004 | 167,002 |
| 31 | OpenCodeInterpreterData | 0.41% | 331,715 | 36,836 |
| 32 | Synthia-v1.3 | 0.41% | 329,115 | 118,841 |
| 33 | yaml | 0.40% | 321,755 | 110,572 |
| 34 | GPTscience_maths_csml | 0.37% | 297,310 | 148,655 |
| 35 | OIG squad_v2 | 0.32% | 260,638 | 19,585 |
| 36 | OIG squad_v2_more_neg | 0.32% | 259,902 | 13,946 |
| 37 | OIG rallio_safety_and_prosocial | 0.31% | 250,534 | 125,235 |
| 38 | MIMIC-medical-report | 0.31% | 250,362 | 83,454 |
| 39 | OIG mathqa_flanv2_kojma_cot | 0.30% | 243,420 | 107,564 |
| 40 | openai_summarize_tldr | 0.29% | 233,336 | 116,668 |
| 41 | OIG sqlv2 | 0.28% | 224,270 | 24,546 |
| 42 | ruby | 0.24% | 197,135 | 68,086 |
| 43 | RPGuild-sharegpt-filtered | 0.24% | 196,309 | 27,053 |
| 44 | OIG multi_news | 0.22% | 179,888 | 89,944 |
| 45 | markdown | 0.22% | 174,608 | 61,260 |
| 46 | javascript | 0.19% | 156,109 | 52,289 |
| 47 | python | 0.19% | 151,866 | 55,045 |
| 48 | know_sql | 0.18% | 148,368 | 49,456 |
| 49 | text | 0.16% | 133,033 | 44,926 |
| 50 | saraswati_stem_formatted | 0.15% | 119,750 | 59,875 |
| 51 | know_saraswati_cot_formatted | 0.14% | 116,408 | 58,204 |
| 52 | json | 0.14% | 115,682 | 39,124 |
| 53 | OIG hc3_human | 0.14% | 112,112 | 56,056 |
| 54 | medical_meadow_medical_flashcards | 0.12% | 100,575 | 33,527 |
| 55 | lmsys-chat-1m-nectar | 0.11% | 86,770 | 43,385 |
| 56 | shell | 0.11% | 85,901 | 30,327 |
| 57 | cogstack-opengpt-sharegpt | 0.10% | 81,667 | 31,532 |
| 58 | Quanta | 0.10% | 78,096 | 26,032 |
| 59 | php | 0.08% | 68,256 | 24,302 |
| 60 | know_logic | 0.08% | 68,208 | 34,104 |
| 61 | html | 0.07% | 57,384 | 19,750 |
| 62 | OIG plot_screenplay_books_dialog | 0.07% | 54,981 | 7,924 |
| 63 | java | 0.07% | 53,574 | 20,150 |
| 64 | Open-Platypus | 0.07% | 53,373 | 24,109 |
| 65 | RFT-GSM-28K | 0.06% | 51,092 | 25,546 |
| 66 | OIG conv_finqa | 0.06% | 50,472 | 9,102 |
| 67 | sharegpt-nectar | 0.06% | 49,896 | 24,948 |
| 68 | OIG cuad | 0.05% | 41,390 | 510 |
| 69 | OpenCerebrum-dpo | 0.05% | 40,534 | 17,013 |
| 70 | Tested-22k-Python-Alpaca | 0.04% | 36,224 | 18,112 |
| 71 | OIG sqlv1 | 0.04% | 34,174 | 17,087 |
| 72 | MedQuad-MedicalQnADataset | 0.04% | 32,718 | 16,359 |
| 73 | piqa | 0.04% | 32,212 | 16,106 |
| 74 | html+erb | 0.04% | 31,679 | 10,708 |
| 75 | OIG image_prompts_instructions | 0.04% | 30,932 | 15,466 |
| 76 | medical_meadow_medqa | 0.04% | 30,534 | 10,178 |
| 77 | ini | 0.04% | 30,461 | 10,396 |
| 78 | medical_meadow_wikidoc | 0.04% | 29,998 | 10,000 |
| 79 | c# | 0.03% | 26,796 | 9,220 |
| 80 | xml | 0.03% | 26,054 | 9,085 |
| 81 | medical_meadow_health_advice | 0.03% | 25,995 | 8,665 |
| 82 | OIG poetry_2_song | 0.03% | 25,462 | 12,731 |
| 83 | flan_v2_niv2-nectar | 0.03% | 24,036 | 12,018 |
| 84 | c | 0.03% | 23,203 | 8,250 |
| 85 | scss | 0.02% | 20,156 | 6,730 |
| 86 | evol_instruct-nectar | 0.02% | 19,930 | 9,965 |
| 87 | ultrachat-nectar | 0.02% | 19,822 | 9,911 |
| 88 | restructuredtext | 0.02% | 18,901 | 6,481 |
| 89 | OpenCerebrum-2.0-SFT | 0.02% | 18,793 | 4,382 |
| 90 | gpteacher-role-play-chatml | 0.02% | 18,222 | 9,111 |
| 91 | OIG grade_school_math_instructions | 0.02% | 17,584 | 8,792 |
| 92 | OIG essays | 0.02% | 17,581 | 2,064 |
| 93 | medical_meadow_wikidoc_patient_information | 0.02% | 17,550 | 5,850 |
| 94 | typescript | 0.02% | 16,912 | 5,816 |
| 95 | coffeescript | 0.02% | 15,836 | 5,403 |
| 96 | go | 0.02% | 14,814 | 4,939 |
| 97 | css | 0.02% | 14,654 | 4,979 |
| 98 | scala | 0.02% | 14,184 | 4,988 |
| 99 | c++ | 0.02% | 13,391 | 4,838 |
| 100 | swift | 0.02% | 13,361 | 4,724 |
| 101 | haml | 0.02% | 12,787 | 4,285 |
| 102 | know_medical_dialogue_v2 | 0.02% | 12,580 | 6,290 |
| 103 | medical_meadow_mmmlu | 0.01% | 11,058 | 3,686 |
| 104 | toml | 0.01% | 10,189 | 3,411 |
| 105 | riddler_formatted | 0.01% | 8,396 | 4,198 |
| 106 | rust | 0.01% | 8,276 | 2,977 |
| 107 | gpt-4-1106-preview | 0.01% | 8,106 | 4,053 |
| 108 | extractor-00000-of-00001 | 0.01% | 7,678 | 3,839 |
| 109 | clojure | 0.01% | 6,974 | 2,394 |
| 110 | Patient-Doctor-Conversation | 0.01% | 6,488 | 3,244 |
| 111 | jsx | 0.01% | 6,390 | 2,176 |
| 112 | kotlin | 0.01% | 6,206 | 2,193 |
| 113 | medical_meadow_mediqa | 0.01% | 6,162 | 2,054 |
| 114 | flan_v2_cot-nectar | 0.01% | 6,000 | 3,000 |
| 115 | perl | 0.01% | 5,837 | 2,217 |
| 116 | mental_health_counseling_conversations | 0.01% | 5,496 | 2,748 |
| 117 | sql | 0.01% | 5,172 | 1,998 |
| 118 | gpt-4-0613 | 0.01% | 4,862 | 2,431 |
| 119 | gpt-3.5-turbo-0613 | 0.01% | 4,742 | 2,371 |
| 120 | nix | 0.01% | 4,704 | 1,582 |
| 121 | false_qa-nectar | 0.01% | 4,640 | 2,320 |
| 122 | unknown | 0.01% | 4,576 | 1,571 |
| 123 | twig | 0.01% | 4,557 | 1,563 |
| 124 | handlebars | 0.01% | 4,176 | 1,405 |
| 125 | haskell | 0.01% | 4,095 | 1,365 |
| 126 | batchfile | 0.00% | 4,003 | 1,409 |
| 127 | less | 0.00% | 3,973 | 1,331 |
| 128 | datasci-python | 0.00% | 3,966 | 1,983 |
| 129 | gpt-4-0314 | 0.00% | 3,962 | 1,981 |
| 130 | groovy | 0.00% | 3,952 | 1,470 |
| 131 | flan_v2_p3-nectar | 0.00% | 3,858 | 1,929 |
| 132 | OIG poetry_instructions | 0.00% | 3,508 | 1,754 |
| 133 | claude-1 | 0.00% | 3,476 | 1,738 |
| 134 | bitbake | 0.00% | 3,419 | 1,264 |
| 135 | claude-2.1 | 0.00% | 3,400 | 1,700 |
| 136 | jade | 0.00% | 3,282 | 1,101 |
| 137 | elixir | 0.00% | 3,281 | 1,138 |
| 138 | claude-instant-1 | 0.00% | 3,262 | 1,631 |
| 139 | viml | 0.00% | 3,150 | 1,050 |
| 140 | slim | 0.00% | 3,111 | 1,043 |
| 141 | emacs-lisp | 0.00% | 2,884 | 983 |
| 142 | cmake | 0.00% | 2,876 | 959 |
| 143 | makefile | 0.00% | 2,721 | 933 |
| 144 | powershell | 0.00% | 2,690 | 970 |
| 145 | cucumber | 0.00% | 2,632 | 951 |
| 146 | llama-2-70b-chat | 0.00% | 2,546 | 1,273 |
| 147 | vicuna-33b | 0.00% | 2,526 | 1,263 |
| 148 | lua | 0.00% | 2,517 | 904 |
| 149 | vicuna-13b | 0.00% | 2,482 | 1,241 |
| 150 | mistral-medium | 0.00% | 2,438 | 1,219 |
| 151 | mixtral-8x7b-instruct-v0.1 | 0.00% | 2,390 | 1,195 |
| 152 | fish | 0.00% | 2,275 | 802 |
| 153 | common-lisp | 0.00% | 2,234 | 761 |
| 154 | smarty | 0.00% | 2,127 | 723 |
| 155 | dart | 0.00% | 2,092 | 750 |
| 156 | sass | 0.00% | 2,060 | 692 |
| 157 | llvm | 0.00% | 1,991 | 778 |
| 158 | claude-2.0 | 0.00% | 1,902 | 951 |
| 159 | saltstack | 0.00% | 1,818 | 617 |
| 160 | gpt-3.5-turbo-1106 | 0.00% | 1,724 | 862 |
| 161 | llama-2-13b-chat | 0.00% | 1,712 | 856 |
| 162 | vue | 0.00% | 1,705 | 583 |
| 163 | diff | 0.00% | 1,564 | 656 |
| 164 | asciidoc | 0.00% | 1,523 | 508 |
| 165 | truthful_qa-nectar | 0.00% | 1,488 | 744 |
| 166 | zephyr-7b-beta | 0.00% | 1,428 | 714 |
| 167 | gpt-3.5-turbo-0314 | 0.00% | 1,418 | 709 |
| 168 | stylus | 0.00% | 1,414 | 476 |
| 169 | freemarker | 0.00% | 1,322 | 508 |
| 170 | erlang | 0.00% | 1,286 | 468 |
| 171 | palm-2 | 0.00% | 1,270 | 635 |
| 172 | hcl | 0.00% | 1,206 | 420 |
| 173 | gpt-4-0125-preview | 0.00% | 1,192 | 596 |
| 174 | html+django | 0.00% | 1,174 | 394 |
| 175 | wizardlm-70b | 0.00% | 1,170 | 585 |
| 176 | wizardlm-13b | 0.00% | 1,140 | 570 |
| 177 | koala-13b | 0.00% | 1,120 | 560 |
| 178 | llama-2-7b-chat | 0.00% | 1,106 | 553 |
| 179 | yi-34b-chat | 0.00% | 1,062 | 531 |
| 180 | qml | 0.00% | 1,053 | 362 |
| 181 | csv | 0.00% | 1,010 | 368 |
| 182 | gemini-pro-dev-api | 0.00% | 954 | 477 |
| 183 | know_medical_dialogues | 0.00% | 952 | 476 |
| 184 | openchat-3.5 | 0.00% | 944 | 472 |
| 185 | flan_v2_flan2021-nectar | 0.00% | 928 | 464 |
| 186 | ocaml | 0.00% | 912 | 327 |
| 187 | gemini-pro | 0.00% | 906 | 453 |
| 188 | pplx-70b-online | 0.00% | 896 | 448 |
| 189 | vicuna-7b | 0.00% | 894 | 447 |
| 190 | codellama-34b-instruct | 0.00% | 852 | 426 |
| 191 | tex | 0.00% | 839 | 297 |
| 192 | starling-lm-7b-alpha | 0.00% | 800 | 400 |
| 193 | rdoc | 0.00% | 795 | 269 |
| 194 | mistral-7b-instruct | 0.00% | 774 | 387 |
| 195 | elm | 0.00% | 772 | 265 |
| 196 | tulu-2-dpo-70b | 0.00% | 756 | 378 |
| 197 | f# | 0.00% | 743 | 251 |
| 198 | alpaca-13b | 0.00% | 710 | 355 |
| 199 | smalltalk | 0.00% | 706 | 284 |
| 200 | oasst-pythia-12b | 0.00% | 684 | 342 |
| 201 | pplx-7b-online | 0.00% | 656 | 328 |
| 202 | ada | 0.00% | 650 | 261 |
| 203 | scheme | 0.00% | 598 | 212 |
| 204 | openhermes-2.5-mistral-7b | 0.00% | 560 | 280 |
| 205 | qwen-14b-chat | 0.00% | 550 | 275 |
| 206 | arduino | 0.00% | 544 | 224 |
| 207 | crystal | 0.00% | 536 | 182 |
| 208 | RWKV-4-Raven-14B | 0.00% | 530 | 265 |
| 209 | gpt-3.5-turbo-0125 | 0.00% | 528 | 264 |
| 210 | gas | 0.00% | 502 | 192 |
| 211 | desktop | 0.00% | 500 | 174 |
| 212 | protocol-buffer | 0.00% | 500 | 180 |
| 213 | julia | 0.00% | 494 | 180 |
| 214 | guanaco-33b | 0.00% | 492 | 246 |
| 215 | haxe | 0.00% | 488 | 173 |
| 216 | groff | 0.00% | 485 | 188 |
| 217 | solar-10.7b-instruct-v1.0 | 0.00% | 484 | 242 |
| 218 | mako | 0.00% | 480 | 166 |
| 219 | glsl | 0.00% | 471 | 157 |
| 220 | java-server-pages | 0.00% | 463 | 163 |
| 221 | chatglm-6b | 0.00% | 432 | 216 |
| 222 | html+php | 0.00% | 432 | 146 |
| 223 | qwen1.5-72b-chat | 0.00% | 426 | 213 |
| 224 | mpt-7b-chat | 0.00% | 426 | 213 |
| 225 | svg | 0.00% | 425 | 166 |
| 226 | mpt-30b-chat | 0.00% | 414 | 207 |
| 227 | stripedhyena-nous-7b | 0.00% | 412 | 206 |
| 228 | html+eex | 0.00% | 405 | 135 |
| 229 | openassistant_oasst1_h2ogpt_llama2_chat | 0.00% | 404 | 202 |
| 230 | qmake | 0.00% | 401 | 135 |
| 231 | fastchat-t5-3b | 0.00% | 388 | 194 |
| 232 | org | 0.00% | 383 | 136 |
| 233 | deepseek-llm-67b-chat | 0.00% | 378 | 189 |
| 234 | llama2-70b-steerlm-chat | 0.00% | 358 | 179 |
| 235 | rhtml | 0.00% | 356 | 124 |
| 236 | cython | 0.00% | 322 | 115 |
| 237 | racket | 0.00% | 321 | 116 |
| 238 | perl6 | 0.00% | 317 | 116 |
| 239 | chatglm3-6b | 0.00% | 314 | 157 |
| 240 | r | 0.00% | 312 | 119 |
| 241 | factor | 0.00% | 287 | 99 |
| 242 | unity3d-asset | 0.00% | 282 | 101 |
| 243 | m4 | 0.00% | 279 | 99 |
| 244 | tcl | 0.00% | 267 | 98 |
| 245 | stablelm-tuned-alpha-7b | 0.00% | 264 | 132 |
| 246 | assembly | 0.00% | 260 | 104 |
| 247 | xslt | 0.00% | 251 | 96 |
| 248 | dolly-v2-12b | 0.00% | 248 | 124 |
| 249 | mind2web-00000-of-00001-fc25d47330eea0fc | 0.00% | 242 | 121 |
| 250 | objective-c++ | 0.00% | 238 | 84 |
| 251 | zephyr-7b-alpha | 0.00% | 236 | 118 |
| 252 | purescript | 0.00% | 225 | 80 |
| 253 | robotframework | 0.00% | 216 | 84 |
| 254 | nous-hermes-2-mixtral-8x7b-dpo | 0.00% | 212 | 106 |
| 255 | standard-ml | 0.00% | 192 | 71 |
| 256 | dolphin-2.2.1-mistral-7b | 0.00% | 190 | 95 |
| 257 | fortran | 0.00% | 187 | 70 |
| 258 | gpt4all-13b-snoozy | 0.00% | 186 | 93 |
| 259 | livescript | 0.00% | 178 | 62 |
| 260 | llama-13b | 0.00% | 176 | 88 |
| 261 | textile | 0.00% | 173 | 60 |
| 262 | nimrod | 0.00% | 173 | 66 |
| 263 | falcon-180b-chat | 0.00% | 156 | 78 |
| 264 | xtend | 0.00% | 155 | 55 |
| 265 | gettext-catalog | 0.00% | 147 | 65 |
| 266 | ceylon | 0.00% | 146 | 49 |
| 267 | chatglm2-6b | 0.00% | 146 | 73 |
| 268 | vala | 0.00% | 143 | 50 |
| 269 | edn | 0.00% | 138 | 47 |
| 270 | awk | 0.00% | 133 | 52 |
| 271 | actionscript | 0.00% | 132 | 48 |
| 272 | visual-basic | 0.00% | 131 | 47 |
| 273 | pod | 0.00% | 130 | 48 |
| 274 | sqf | 0.00% | 127 | 43 |
| 275 | openchat-3.5-0106 | 0.00% | 126 | 63 |
| 276 | dockerfile | 0.00% | 115 | 39 |
| 277 | linker-script | 0.00% | 108 | 36 |
| 278 | idris | 0.00% | 107 | 37 |
| 279 | qwen1.5-7b-chat | 0.00% | 102 | 51 |
| 280 | solidity | 0.00% | 102 | 36 |
| 281 | systemverilog | 0.00% | 101 | 35 |
| 282 | json5 | 0.00% | 98 | 33 |
| 283 | jupyter-notebook | 0.00% | 98 | 47 |
| 284 | processing | 0.00% | 96 | 35 |
| 285 | mediawiki | 0.00% | 94 | 33 |
| 286 | rouge | 0.00% | 92 | 41 |
| 287 | xquery | 0.00% | 89 | 38 |
| 288 | graphviz-dot | 0.00% | 84 | 32 |
| 289 | liquid | 0.00% | 83 | 29 |
| 290 | thrift | 0.00% | 77 | 28 |
| 291 | groovy-server-pages | 0.00% | 75 | 25 |
| 292 | pan | 0.00% | 69 | 23 |
| 293 | qwen1.5-4b-chat | 0.00% | 68 | 34 |
| 294 | api-blueprint | 0.00% | 67 | 23 |
| 295 | opencl | 0.00% | 66 | 23 |
| 296 | asp | 0.00% | 64 | 22 |
| 297 | cuda | 0.00% | 64 | 25 |
| 298 | logtalk | 0.00% | 63 | 21 |
| 299 | pascal | 0.00% | 62 | 24 |
| 300 | chapel | 0.00% | 60 | 20 |
| 301 | sparql | 0.00% | 60 | 23 |
| 302 | coldfusion-cfc | 0.00% | 58 | 20 |
| 303 | applescript | 0.00% | 57 | 19 |
| 304 | parrot-internal-representation | 0.00% | 56 | 20 |
| 305 | logos | 0.00% | 55 | 19 |
| 306 | mistral-7b-instruct-v0.2 | 0.00% | 54 | 27 |
| 307 | literate-coffeescript | 0.00% | 54 | 19 |
| 308 | digital-command-language | 0.00% | 53 | 19 |
| 309 | turtle | 0.00% | 52 | 21 |
| 310 | ioke | 0.00% | 52 | 19 |
| 311 | pony | 0.00% | 48 | 16 |
| 312 | openscad | 0.00% | 48 | 21 |
| 313 | vcl | 0.00% | 48 | 17 |
| 314 | graphql | 0.00% | 48 | 17 |
| 315 | dm | 0.00% | 46 | 16 |
| 316 | gnuplot | 0.00% | 45 | 17 |
| 317 | ooc | 0.00% | 43 | 15 |
| 318 | inno-setup | 0.00% | 43 | 15 |
| 319 | gentoo-ebuild | 0.00% | 42 | 15 |
| 320 | modelica | 0.00% | 42 | 15 |
| 321 | antlr | 0.00% | 42 | 15 |
| 322 | nsis | 0.00% | 41 | 15 |
| 323 | http | 0.00% | 38 | 18 |
| 324 | ninja | 0.00% | 36 | 14 |
| 325 | mirah | 0.00% | 36 | 15 |
| 326 | autohotkey | 0.00% | 36 | 15 |
| 327 | augeas | 0.00% | 35 | 13 |
| 328 | hy | 0.00% | 32 | 11 |
| 329 | hlsl | 0.00% | 32 | 11 |
| 330 | stata | 0.00% | 30 | 10 |
| 331 | piglatin | 0.00% | 30 | 11 |
| 332 | capn-proto | 0.00% | 28 | 10 |
| 333 | moonscript | 0.00% | 28 | 10 |
| 334 | coldfusion | 0.00% | 27 | 9 |
| 335 | volt | 0.00% | 27 | 9 |
| 336 | tcsh | 0.00% | 25 | 10 |
| 337 | jasmin | 0.00% | 25 | 9 |
| 338 | raml | 0.00% | 25 | 9 |
| 339 | postscript | 0.00% | 25 | 9 |
| 340 | scilab | 0.00% | 25 | 10 |
| 341 | fancy | 0.00% | 24 | 8 |
| 342 | gdscript | 0.00% | 24 | 8 |
| 343 | latte | 0.00% | 21 | 7 |
| 344 | aspectj | 0.00% | 20 | 7 |
| 345 | apl | 0.00% | 20 | 7 |
| 346 | xs | 0.00% | 20 | 7 |
| 347 | g-code | 0.00% | 19 | 7 |
| 348 | nesc | 0.00% | 19 | 7 |
| 349 | emberscript | 0.00% | 19 | 7 |
| 350 | ston | 0.00% | 18 | 6 |
| 351 | oz | 0.00% | 18 | 7 |
| 352 | literate-haskell | 0.00% | 18 | 7 |
| 353 | yang | 0.00% | 17 | 6 |
| 354 | webidl | 0.00% | 17 | 6 |
| 355 | jsonld | 0.00% | 16 | 6 |
| 356 | jsoniq | 0.00% | 16 | 6 |
| 357 | lfe | 0.00% | 16 | 6 |
| 358 | pike | 0.00% | 15 | 6 |
| 359 | purebasic | 0.00% | 15 | 5 |
| 360 | pov-ray-sdl | 0.00% | 14 | 5 |
| 361 | lilypond | 0.00% | 13 | 6 |
| 362 | agda | 0.00% | 13 | 5 |
| 363 | vhdl | 0.00% | 13 | 5 |
| 364 | zephir | 0.00% | 12 | 4 |
| 365 | mupad | 0.00% | 12 | 4 |
| 366 | mask | 0.00% | 12 | 4 |
| 367 | krl | 0.00% | 12 | 4 |
| 368 | zig | 0.00% | 12 | 4 |
| 369 | metal | 0.00% | 12 | 4 |
| 370 | slash | 0.00% | 12 | 4 |
| 371 | io | 0.00% | 12 | 4 |
| 372 | monkey | 0.00% | 12 | 4 |
| 373 | ragel-in-ruby-host | 0.00% | 10 | 4 |
| 374 | xbase | 0.00% | 9 | 3 |
| 375 | eagle | 0.00% | 9 | 4 |
| 376 | squirrel | 0.00% | 9 | 4 |
| 377 | genshi | 0.00% | 9 | 3 |
| 378 | cartocss | 0.00% | 9 | 3 |
| 379 | xproc | 0.00% | 9 | 3 |
| 380 | wisp | 0.00% | 9 | 3 |
| 381 | urweb | 0.00% | 9 | 3 |
| 382 | yacc | 0.00% | 8 | 3 |
| 383 | smt | 0.00% | 8 | 3 |
| 384 | medical_meadow_pubmed_causal | 0.00% | 8 | 4 |
| 385 | lsl | 0.00% | 8 | 3 |
| 386 | ats | 0.00% | 8 | 3 |
| 387 | flux | 0.00% | 8 | 3 |
| 388 | bro | 0.00% | 8 | 3 |
| 389 | ecl | 0.00% | 8 | 4 |
| 390 | nit | 0.00% | 7 | 3 |
| 391 | pawn | 0.00% | 7 | 3 |
| 392 | rebol | 0.00% | 7 | 3 |
| 393 | mtml | 0.00% | 6 | 2 |
| 394 | eiffel | 0.00% | 6 | 2 |
| 395 | c2hs-haskell | 0.00% | 6 | 2 |
| 396 | uno | 0.00% | 6 | 2 |
| 397 | lean | 0.00% | 6 | 3 |
| 398 | sourcepawn | 0.00% | 6 | 3 |
| 399 | brainfuck | 0.00% | 6 | 2 |
| 400 | renpy | 0.00% | 6 | 2 |
| 401 | boo | 0.00% | 6 | 2 |
| 402 | arc | 0.00% | 6 | 2 |
| 403 | dylan | 0.00% | 6 | 2 |
| 404 | bluespec | 0.00% | 6 | 2 |
| 405 | creole | 0.00% | 6 | 2 |
| 406 | forth | 0.00% | 6 | 2 |
| 407 | apacheconf | 0.00% | 6 | 2 |
| 408 | isabelle | 0.00% | 5 | 2 |
| 409 | maple | 0.00% | 5 | 2 |
| 410 | dns-zone | 0.00% | 5 | 2 |
| 411 | nginx | 0.00% | 5 | 2 |
| 412 | inform-7 | 0.00% | 5 | 2 |
| 413 | csound | 0.00% | 4 | 2 |
| 414 | nu | 0.00% | 4 | 2 |
| 415 | supercollider | 0.00% | 4 | 2 |
| 416 | parrot-assembly | 0.00% | 3 | 1 |
| 417 | literate-agda | 0.00% | 3 | 1 |
| 418 | igor-pro | 0.00% | 3 | 1 |
| 419 | unrealscript | 0.00% | 3 | 1 |
| 420 | pure-data | 0.00% | 3 | 1 |
| 421 | blitzmax | 0.00% | 3 | 1 |
| 422 | sage | 0.00% | 3 | 1 |
| 423 | module-management-system | 0.00% | 3 | 1 |
| 424 | scaml | 0.00% | 3 | 1 |
| 425 | netlinx | 0.00% | 3 | 1 |
| 426 | abap | 0.00% | 3 | 1 |
| 427 | xpages | 0.00% | 3 | 1 |
| 428 | propeller-spin | 0.00% | 3 | 1 |
| 429 | sas | 0.00% | 3 | 1 |
| 430 | ArithmeLogic | 0.00% | 2 | 1 |
| 431 | clean | 0.00% | 2 | 1 |
| 432 | harbour | 0.00% | 2 | 1 |
| 433 | mathematica | 0.00% | 2 | 1 |
| 434 | jflex | 0.00% | 2 | 1 |
| 435 | red | 0.00% | 2 | 1 |

Citations

@misc{ibrahim2024simple,
      title={Simple and Scalable Strategies to Continually Pre-train Large Language Models}, 
      author={Adam Ibrahim and Benjamin Thérien and Kshitij Gupta and Mats L. Richter and Quentin Anthony and Timothée Lesort and Eugene Belilovsky and Irina Rish},
      year={2024},
      eprint={2403.08763},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@misc{jain2023neftune,
      title={NEFTune: Noisy Embeddings Improve Instruction Finetuning}, 
      author={Neel Jain and Ping-yeh Chiang and Yuxin Wen and John Kirchenbauer and Hong-Min Chu and Gowthami Somepalli and Brian R. Bartoldson and Bhavya Kailkhura and Avi Schwarzschild and Aniruddha Saha and Micah Goldblum and Jonas Geiping and Tom Goldstein},
      year={2023},
      eprint={2310.05914},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{wang2020optimistic,
      title={An Optimistic Acceleration of AMSGrad for Nonconvex Optimization}, 
      author={Jun-Kun Wang and Xiaoyun Li and Belhal Karimi and Ping Li},
      year={2020},
      eprint={1903.01435},
      archivePrefix={arXiv},
      primaryClass={stat.ML}
}

@misc{keskar2017improving,
      title={Improving Generalization Performance by Switching from Adam to SGD}, 
      author={Nitish Shirish Keskar and Richard Socher},
      year={2017},
      eprint={1712.07628},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@misc{mukherjee2023orca,
      title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, 
      author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
      year={2023},
      eprint={2306.02707},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
Downloads last month
41
Edit dataset card