[{"data":1,"prerenderedAt":231},["ShallowReactive",2],{"project-24561214":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":31,"aspects":32,"strip":35,"post_text":37,"what":38,"said":77,"maker_in_thread":147,"shape":156,"grid":159,"attempts":193,"same_week":194,"maker_shows":157,"maker_hidden":224,"reader_version":225,"card":226},"24561214","booste.io pretrained models API","A free-to-use GPT-2 API","title","Show HN: I made a free-to-use GPT-2 API","https:\u002F\u002Fwww.booste.io\u002Fpretrained-models","booste.io","edunteman",1600817102,2020,70,19,872,3028,29,"notable","ai","nlp model api","api",[24,25,26,27],"gpt-2","text generation api","nlp api","pretrained models","curious",0,{"positive":29,"neutral":31,"mixed":29,"critical":29},6,{"idea":33,"pricing":34},{"positive":29,"critical":29},{"positive":29,"critical":29},[29,29,29,29,29,29,36,36,29,29,36,29,36,29,29,36,29,36,29],3,null,{"problem":39,"audience":37,"pricing":46,"motivation":55,"time_to_build":37,"stack":59,"openness":74,"stage":75,"team_size":76},{"value":40,"source":41,"evidence":42},"Makes using pretrained ML models as simple as a one-line API call","maker",[43],{"id":44,"by":11,"text":45},"24561215","Hey HN, I recently launched this GPT-2 API, and figured you'd be into it. The goal is simplicity, so you hit the endpoint with a one-line call from the Python client. Here's a…",{"value":47,"source":41,"evidence":48},"Free to use for pretrained models; add-ons may cost later; about $40\u002Fmonth hosting cost",[49,52],{"id":50,"by":11,"text":51},"24562151","I'd like to keep pretrained models free, so this current experience should stay free. Add-ons such as style transfer logic or any form of personalization on the model would have…",{"id":53,"by":11,"text":54},"24634537","Bout $40\u002Fmonth. I'm running on https:\u002F\u002Fzeet.co",{"value":56,"source":41,"evidence":57},"Make the ML stack as simple as Stripe made payments",[58],{"id":44,"by":11,"text":45},[60,64,70],{"value":61,"source":41,"evidence":62},"Python client",[63],{"id":44,"by":11,"text":45},{"value":65,"source":41,"evidence":66},"TF Serving",[67],{"id":68,"by":11,"text":69},"24634525","UPDATE: (a week later): I've gutted my infrastructure and moved to TF Serving. Haven't had a downtime event in the 30 hrs it's been live. Jump on the waitlist for updates :)",{"value":71,"source":41,"evidence":72},"Zeet hosting",[73],{"id":53,"by":11,"text":54},"free","launched","unknown",{"praise":78,"objections":91,"requests":107,"questions":120,"alternatives":139},[79],{"value":80,"source":81,"evidence":82},"Interesting idea, useful for simple NLP use","commenter",[83,87],{"id":84,"by":85,"text":86},"24561780","ghoomketu","This looks very cool. It says on the website \"Predict the next word(s) from a given sequence of words.\" Speaking as someone who has very little programming knowledge, would it be…",{"id":88,"by":89,"text":90},"24561516","furqanrydhan","This is cool, adding any CV models soon? Have a couple idea's around video streams and fitness that i'd like to explore",[92,101],{"value":93,"source":41,"evidence":94},"Service has downtime and infrastructure limits under load",[95,98],{"id":96,"by":11,"text":97},"24562188","UPDATE: First time launching this to larger audience, and hitting infra limits. It's self healing, but please be patient if an error throws; try back in 3 minutes. I'm working to…",{"id":99,"by":11,"text":100},"24563206","UPDATE: (as of 36 upvotes): Thanks everyone for trying it out and hitting me with the traffic. Great Show HN. Found a memory leak. Luckily it self heals on crash, so downtime is…",{"value":102,"source":41,"evidence":103},"Not open source",[104],{"id":105,"by":11,"text":106},"24562102","It's not, sorry :(",[108,112],{"value":109,"source":81,"evidence":110},"Add computer vision models",[111],{"id":88,"by":89,"text":90},{"value":113,"source":81,"evidence":114},"Personalize output to a user's writing style",[115,116],{"id":84,"by":85,"text":86},{"id":117,"by":118,"text":119},"24561920","knicholes","You fine-tune the end layers of the network with your own writing. This, however, requires the model.",[121,128],{"value":122,"source":81,"evidence":123},"Is it open source?",[124],{"id":125,"by":126,"text":127},"24562070","single_source","Is this open source? Any link to a repo?",{"value":129,"source":81,"evidence":130},"What does it cost to run?",[131,135],{"id":132,"by":133,"text":134},"24562137","efrank02","How much will this cost you each month?",{"id":136,"by":137,"text":138},"24574522","abiogenesis","I think the question was how much you are paying to maintain this.",[140],{"value":141,"source":81,"evidence":142},"Fabrice Bellard's GPT-2 inference binary (gpt2tc)",[143],{"id":144,"by":145,"text":146},"24562207","rahimnathwani","Related, Fabrice Bellard developed a C program for GPT-2 inference. It's not open source, but the binary is free to download, and can use any pretrained GPT-2 model:…",{"comments":148,"answered":149,"key":150},11,4,[151,152,153],{"id":44,"text":45},{"id":96,"text":97},{"id":154,"text":155},"24562357","UPDATE: (as of 24 upvotes on main post). I scaled up my infra. It should be more stable at current load. Please continue to be patient; y'all are great.",{"commenters":157,"max_depth":149,"maker_replies":148,"first_comment_mins":29,"lifespan_hours":158},8,169,[160,163,165,166,167,169,172,173,174,176,178,179,181,184,185,188,190,191,192],[44,29,29,161,11,162],"project\u002Fneutral\u002Fidea",1,[96,162,29,164,11,162],"project\u002Fneutral\u002Fperformance",[154,162,29,164,11,162],[99,162,29,164,11,162],[68,162,29,168,11,162],"project\u002Fpositive\u002Fperformance",[144,170,29,171,145,29],2,"other\u002Fneutral\u002Fnone",[84,36,36,161,85,29],[117,36,36,161,118,29],[175,36,29,161,11,162],"24562016",[177,36,29,161,11,162],"24562037",[88,149,36,161,89,29],[180,149,29,161,11,162],"24561575",[125,182,36,183,126,29],5,"project\u002Fneutral\u002Fnone",[105,182,29,183,11,162],[186,182,29,187,126,29],"24562234","commenter\u002Fpositive\u002Fnone",[132,31,36,189,133,29],"project\u002Fneutral\u002Fpricing",[50,31,29,189,11,162],[136,31,36,189,137,29],[53,31,29,189,11,162],[],[195,200,205,210,215,219],{"id":196,"name":197,"points":198,"category":199},"24564684","Mono Icons",333,"creative",{"id":201,"name":202,"points":203,"category":204},"24517925","ugit",309,"learning_science",{"id":206,"name":207,"points":208,"category":209},"24528479","chromecast_mpris",222,"dev_tools",{"id":211,"name":212,"points":213,"category":214},"24572449","Open-Source Memex",188,"productivity",{"id":216,"name":217,"points":218,"category":214},"24544183","Annotate.tv",154,{"id":220,"name":221,"points":222,"category":223},"24538977","rubyspeed",153,"languages",false,"v2",{"id":227,"name":5,"line":6,"ai":224,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":228,"maker":11,"domain":10,"tier":19,"attempts":29,"strip":229,"url":9,"mix":230,"praise":80,"objection":93,"sub":21},24561214,[24,25,26,27],"0000003300303003030",[29,31,29,29],1793991016498]