Cishe usuvele ujwayelene namathuluzi afana ne-ChatGPT, i-Claude, noma i-Gemini. Nakuba emangalisa, kukhona into eyodwa encane ongayibamba: asebenza efwini. Lokhu kusho ukuthi igama ngalinye olibhalayo liya kumaseva enkampani, okungaba yinkinga kancane. udaba olubucayi lobumfihlo uma uphatha idatha eyimfihlo noma usebenza emikhakheni lapho umthetho uvimbela khona ulwazi ukuthi luphume ehhovisi.
Yilapho i-Ollama ingena khona, uhlelo lokusebenza oluguqula ikhompyutha yakho ibe yi- Isikhungo sezinzwa se-AIKhohlwa ngokubhalisa kwanyanga zonke nokuthembela ekuxhumekeni kwe-inthanethi okuzinzile; ngaleli thuluzi ungalanda amathempulethi omthombo ovulekile bese uwasebenzisa ngqo kwihadiwe yakho, ugcine ukulawula okuphelele kwedatha yakho.
Iyini ngempela i-Ollama futhi yiziphi izinzuzo zayo?
I-Ollama iyisofthiwe yomthombo ovulekile esebenza njengeklayenti lokuphatha amamodeli olimi olubanzi (i-LLM). Amandla ayo amakhulu ukuthi kwenza kube lula ukuba yinkimbinkimbi kobuchwepheshe, ukunakekela ukulungiswa kwe-GPU kanye nokuphathwa kwememori ukuze ukwazi ukusebenzisa umyalo owodwa kuphela bese uqala ukuxoxa.
Izinzuzo zicacile. Okokuqala, Ubumfihlo buphelele Njengoba kungekho lutho oluphuma emshinini wakho. Okwesibili, wonga ezindlekweni zethokheni ye-API noma ezindlekweni zohlelo lwe-Plus zanyanga zonke. Okwesithathu, uma imodeli isiku-hard drive yakho, ungayisebenzisa. ungaxhunyiwe ku-inthanethi ngokupheleleKuhle kakhulu uma usendizeni noma ezindaweni ezimbozwe kabi.
Kodwa-ke, akusikho konke ukukhanya kwelanga nama-rose. Inkinga enkulu ukuthi Udinga ihadiwe enamandlaUma uzama ukusebenzisa imodeli enkulu kwi-PC ene-RAM encane, impendulo izoba kancane kangangokuthi uzoba nesikhathi sokwenza ikhofi ngaphambi kokuba iqede umusho. Ngaphezu kwalokho, i-AI yazi kuphela lokho ekufundile kuze kube usuku lwayo lokuqeqeshwa, ngakho ayinakho ukufinyelela ezindabeni ezisheshayo ngesikhathi sangempela.
Izidingo zesistimu kanye nehadiwe enconywayo
Ukuze ugweme okuhlangenwe nakho okukhungathekisayo, kufanele ubheke izingxenye zakho. Umthombo obaluleke kakhulu yi- I-RAM ne-VRAM yekhadi lakho lehluzo. Njengomthetho ojwayelekile, imodeli engu-1.5B ithatha cishe isikhala esingu-1GB, kodwa idinga inkumbulo eyengeziwe ukuze isebenze kahle.
- Amamodeli Amancane (270M kuya ku-4B): Kulungele imishini ephansi noma ephathwayo.
- Amamodeli Amancane (4B kuya ku-14B): Inketho elinganiselayo yomsebenzisi wasekhaya.
- Amamodeli Aphakathi (14B kuya ku-70B): Lapha udinga ihadiwe engathi sína.
- Amamodeli Amakhulu (angaphezu kuka-70B): Kuphela kwemishini enezinsizakusebenza ezinkulu.
Ngokuphathelene ne-GPU, ukuba ne-NVIDIA ene-CUDA, i-AMD ene-ROCm, noma i-Mac ene-Apple Metal kwenza umehluko omkhulu, kusheshiswe ukwenziwa kombhalo. phakathi kwezikhathi ezi-5 neziyi-10 Ngokuphathelene nokusebenzisa i-CPU kuphela: Uma uzothenga imishini, funa amakhadi ehluzo ane-VRAM okungenani engu-16GB ukuze ungaphelelwa yisikhathi ngokushesha.
Umhlahlandlela wokufaka wesinyathelo ngesinyathelo
Ukufaka i-Ollama kulula ngokumangazayo futhi kungenziwa ngemizuzu embalwa kuye ngohlelo lokusebenza olusebenzisayo:
En WindowsMane nje ulande ifayela le-.exe kuwebhusayithi esemthethweni. Ngokuvamile lizofakwa kufolda ye-AppData yomsebenzisi. Kulabo abathanda izitsha, lingaphinde lisetshenziswe kusetshenziswa Ideskithophu yeDocker, isebenzisa umyalo wokufaka osemthethweni kutheminali.
Okwabasebenzisi be LinuxIndlela esheshayo ukusebenzisa i-terminal enomyalo curl -fsSL https://ollama.com/install.sh | shUma isifakiwe, isevisi ivame ukusebenza ngemuva. Uma udinga ukushintsha lapho amamodeli agcinwa khona ukuze ugweme ukugcwalisa idiski yakho eyinhloko, ungahlela i-environment variable. OVEN_MODELS kufayela lokucushwa kwesevisi yesistimu.
En macOSUkufakwa kulula kakhulu kusetshenziswa isifaki esilandiwe noma ngisho nokusebenzisa brew install ollamaUhlelo luzosebenzisa ngokuzenzakalelayo i- Ukusheshisa kwensimbi ama-chips e-Apple Silicon.
Indlela yokuphatha nokusebenzisa amamodeli e-AI
Uma iseva ye-Ollama isisebenza (uzoyibona kusithonjana sebha yomsebenzi), ungaqala ukulanda amamodeli. Umyalo oyisisekelo uthi ollama pull [nombre-del-modelo]noma ngabe usebenzisa ollama run, uhlelo izolanda imodeli ngokuzenzakalelayo uma ungakabi nayo.
Kunezinhlobo ezahlukene zamamodeli kuye ngezidingo zakho:
- Ingxoxo: I-Llama 3 noma i-Mistral yizona zinkosi lapha ngenxa yokulinganisela kwazo phakathi kwekhwalithi kanye nesivinini.
- Ukuhlela: I-CodeLlama noma i-DeepSeek-Coder zilungele ukulungisa amaphutha ekhodi noma ukukhiqiza imisebenzi.
- I-Multimodal (Umbono): Amamodeli afana ne-LLaVA akuvumela ukuthi ulayishe izithombe bese ucela i-AI ukuthi izichaze.
- Ukuzindla (Ukucabanga): Amamodeli aklanyelwe ukuchaza izinqubo isinyathelo ngesinyathelo.
Ukuze uhlanganyele, mane usebenzise ollama run llama3 futhi uzofaka umyalo osebenzisanayo. Ngaphakathi kwalesi sikhathi, ungasebenzisa imiyalo efana nokuthi /? ngosizo noma /bye Ukuze uphume. Uma ufuna ukubona ukuthi yini oyifakile, ollama list Izokunikeza uhlu oluphelele, kanye ollama ps Ungahlola ukuthi imodeli iyasebenza yini kulayishwe ku-GPU noma ku-CPU.
Izilungiselelo ezithuthukisiwe kanye nokwenza ngezifiso
Uma ungumthuthukisi, i-Ollama iyimayini yegolide ngoba iveza I-REST API ku-port 11434Lokhu kukuvumela ukuthi uxhume i-AI yendawo kunoma yiluphi uhlelo lokusebenza. Iyahambisana nefomethi ye-OpenAI, ngakho ungayihlanganisa ku-VS Code nge-GitHub Copilot (usebenzisa inketho ye-BYOK) noma usebenzise ama-ejenti afana ne-OpenCode.
Esinye isici esinamandla yi- Ifayela lemodeliKufana ne-Dockerfile kodwa nge-AI. Ikuvumela ukuthi udale inguqulo yangokwezifiso yemodeli ngokuchaza i- Ukwaziswa Kwesistimu ethize (isibonelo, ukuguqula i-Llama ibe uchwepheshe kwezomthetho waseSpain), lungisa izinga lokushisa ukuze lenze libe nobuciko noma libe nembe kakhudlwana, bese ulondoloza lokho kulungiselelwa ngaphansi kwegama elifanele.
Kulabo abafuna isikhombikubona esibonakalayo esifana kakhulu ne-ChatGPT, isincomo ukufaka Vula i-WebUIIxhuma ku-Ollama njenge-backend futhi ikunikeza ulwazi oluphelele lwewebhu ngomlando wengxoxo kanye nokuphathwa kwedokhumenti, konke kusebenza kunethiwekhi yakho yendawo.
Amathiphu okuthuthukisa nokusebenza kahle
Uma ubona ukuthi i-AI ihamba kancane, isinyathelo sokuqala ukuhlola quantizationLe nqubo yehlisa ukunemba kwezisindo zemodeli (kusukela kuma-bits angu-16 kuya kuma-bits angu-4 noma angu-8, isibonelo), okunciphisa kakhulu i-RAM edingekayo ngaphandle kokulahlekelwa ikhwalithi eningi kakhulu. Q4_K_M Ngokuvamile kuyindawo emnandi phakathi kokusebenza kahle nokunemba.
Ukuze uvimbele i-Ollama ekusebenziseni izinsiza uma ungayisebenzisi, ungakhubaza i- ukuqala okuzenzakalelayo ku-Windows Task Manager. Kuwusizo futhi ukuqapha ukusetshenziswa kwe-VRAM ngesikhathi sangempela ukuze ubone ukuthi imodeli iyayenza yini iyalayisha ku-RAM yesistimu, okunciphisa kakhulu ijubane lokuphendula.
Ukulawula ingqalasizinda yendawo kwenza ukusetshenziswa kobuhlakani bokwenziwa kube yintando yeningi, kususwe izithiyo zomnotho zokubhalisela kanye nezingozi zokuphepha zefu. Ngokuhlanganisa amandla amamodeli afana ne-Llama 3 noma i-Mistral kanye nokuphathwa kalula kwe-Ollama, noma yimuphi umthandi noma inkampani ingasungula eyayo. uhlelo lwe-AI oluyimfihlo, ukwenza ngcono ihadiwe etholakalayo kanye nokwenza ngezifiso ukuziphatha kwamamodeli ngokusebenzisa ama-Modelfiles nama-API ahlanganisiwe.