Bibliothèque IA gratuite

IA làkk tegtalMoom ba fàww.

155 guide yu leer ci Àngle, yooni jàng yuñ yamale, ak bibliotek bu ubbeeku — bi 501(c)(3) mbootaay bu moom boppam tabax ngir ku nekk mëna xam IA bu bees bi.

155Gid yu amul fayda
1topic topic
~2 minguide bu nekk
~5hJamonoy jàng

Tambalil fii

Juroom njàngale yu lalu ci njariñ

Njang moomu dafay àndaale ak ay njariñ yu leer, ay mënin yuñ mëna def ci kàrt, ay liggéey yuñ ciy jëfandikoo, ak benn capstone buñ jëfandikoo.

topic topic

Saytu ci piste

Tëmb ci barab bi nga bëgg. Bépp track amna guide yu bari ci Àngle bu leer.

Fondamentaal yiBaatu-jàngat yi: ni IA di doxee ci dayo bu kawe.84 tegtal IA làkkLLMs, PNL, ChatGPT, laaj, ak xam mbind.155 tegtal IA buy waneDefar nataal, xool ordinatër, wideo ak jëmmal.133 tegtal Audio IABaat, music, podcast, ak IA bu njëkk ci audio.117 tegtal Sosiete yiProfil yu OpenAI, Anthropic, Google, Meta, ak yeneen.121 tegtal Aplikaasioŋ yiNaka IA di feeñee ci kodage, seetlu, ndawu liggéey ak dundu bis bu nekk.111 tegtal Liggéeyukaay yiIA ci wàllu faju, xaalis, njàng, kuuraŋ ak yeneen mbir.91 tegtal XaralaPuce yi, ajustement bu baax, RAG, vecteur ak jumtukaayi IA.177 tegtal Askan wiTeg sa bopp, nëbbëtu, yelleefu moomeel, kaaraange, ak ëlëgu IA.30 tegtal

Bibliothèque bu mat

guide yépp

155 de 1019 tegtal yi ñu wane. Seggal ci track wala seetlu ci kaw.

IA làkk

Kahneman-Tversky

Kahneman-Tversky Optimization (KTO) xeetu méngale la buy jàngee ci etiketu baraam-ci kaw wala baraam-ci suuf ci barabu méngale ñaar.

2 min lireLiir
IA làkk

Réjection de échantillonnage de rejection

Rejection Sampling Fine-Tuning (RFT) dafay defar tontu yu bari ci kàndidaa yi, bàyyi ci ñi gëna am poñ, ba noppi tàggataat xeetu tontu yooyu ci ñi jël raw gàddu gi.

2 min lireLiir
IA làkk

Modelu neexal ci liggéey

Modèlu neexal yi (PRMs) dañuy joxe poñ ci jéego bu nekk ci xalaatu IA bi, du tontu bu mujj bi kese.

2 min lireLiir
IA làkk

Aggrégation njaxasu Agent

Mixture-of-Agents (MoA) xarala la boo xamni xeeti làkk yu bari dañuy bind ay tontu, ginaaw ga ñu boole seeni xalaat yu gëna baax ci benn xeetu làkk bu gëna baax...

2 min lireLiir
IA làkk

Adaptatëru couche ngir toxal

Adaptateur layers yi ay module yu ndaw lañu yuñ mëna tàggat, ñu dugal leen ci model buñ tàggat bu njëkk, loolu dina tax nga mëna ànd ak liggéey yu bees soo yeesal ay pursaa yu néew...

2 min lireLiir
IA làkk

Bopp yu bari yu nëbbu

Multi-Head Latent Attention (MLA) jumtukaay la buy bàyyi xel, ñu dugal ko ci DeepSeek-V2, muy tënk cache bu am valeur bu bari mémoire ci benn cache bu ndaw buñ bokk...

2 min lireLiir
IA làkk

Medusa boppu dekodaas

Medusa xeetu dekodaasu speculatif la buy boole ay 'bopp' yuy wax luy waaja am ci benn xeetu làkk suko defee mu mëna xayma ay jeton yu bari ci ëlëg benn yoon.

2 min lireLiir
IA làkk

Njaxasu xóotaayu

Njaxasu xóotaayu (MoD) dafay may transformatër bi mu jëfandikoo ay lim yu wuute ci ay jeton yu wuute, di yóbbu jeton yu 'am solo' yi ci layer bu nekk...

2 min lireLiir
IA làkk

Mamba ak barabi réew yuñ tànn

Mamba xeetu toppalante la buñ tabax ci kaw xeetu espaas yu réew mi (SSMs) yuy doxal mbind ci diir bu ligneer, di joxe beneen anam bu gaaw ci Transformer quadratic...

2 min lireLiir
IA làkk

RWKV Lineer

RWKV architecture la buy tàggat ni Transformer waaye di doxal inference ni reso buy baaxoo, di joxe temps ligneer, defar mémoire buy wéy.

2 min lireLiir
IA làkk

Modèlu attention bu néew

Bayyi xel bu néew dafay tax Transformers gëna xéewale ndax dafay bàyyi token bu nekk mu bàyyi xel ci benn subset buñ tànn bu baax ci yeneen token yi, du leen ñépp.

2 min lireLiir
IA làkk

QLoRA ak 4-bit

QLoRA xarala la bu lay may nga defar modelu làkk bu mag ci benn GPU konsomatër ci denc model bu liw ci 4 bits ci poid bu nekk.

2 min lireLiir

Jeexal nga jàng? Firndeel ko.

Check what you learned with a topic quiz, then explore our structured courses or work toward a certificate. Every guide stays free to read.

Natt li nga jàngAm sertifikaaJoxe ndimbalJàng sunu misiyon