Différences

Ci-dessous, les différences entre deux révisions de la page.

--- aitextgen [2021/08/21 15:34] – ↷ Liens modifiés en raison d'un déplacement. 23.92.22.213
+++ aitextgen [2022/02/08 15:59] (Version actuelle) – Tag0 Removed: text_gen serge
@@ Ligne 25: / Ligne 25: @@
   * **[[https://towardsdatascience.com/representing-text-in-natural-language-processing-1eead30e57d8|Representing text in natural language processing]]**
   * **[[https://nlp.stanford.edu/pubs/glove.pdf|GloVe: Global Vectors for Word Representation]]**
-=====Quel carte graphique choisir en Juin 2020=====
-  * **[[https://lambdalabs.com/blog/choosing-a-gpu-for-deep-learning/|Choosing the Best GPU for Deep Learning in 2020]]**
-    * RTX 2060 (6 GB): if you want to explore deep learning in your spare time. 360€
-    * RTX 2070 or 2080 (8 GB): if you are serious about deep learning, but your GPU budget is $600-800. Eight GB of VRAM can fit the majority of models.
-    * RTX 2080 Ti (11 GB): if you are serious about deep learning and your GPU budget is ~$1,200. The RTX 2080 Ti is ~40% faster than the RTX 2080.
-    * Titan RTX and Quadro RTX 6000 (24 GB): if you are working on SOTA models extensively, but don't have budget for the future-proofing available with the RTX 8000. 4000€
-    * Quadro RTX 8000 (48 GB): you are investing in the future and might even be lucky enough to research SOTA deep learning in 2020. 5500€
 ===== Ressources =====
 ====aitextgen====
@@ Ligne 347: / Ligne 340: @@
   * **[[https://github.com/sergeLabo/fables_gpt2_small|fables_gpt2_small]]**
-=====Comment construire à partir d'un BERT model=====
-<WRAP center round todo 60%>
-Veille technologique à suivre ..........
-</WRAP>
-  * https://camembert-model.fr/ construit avec https://oscar-corpus.com/
-  * https://en.wikipedia.org/wiki/Natural-language_generation Natural-language generation NLG
-  * https://prakhartechviz.blogspot.com/2020/04/natural-language-generation-using-bert.html Can BERT be used to generate Natural Language? Yes, BERT can be used for generating Natural Language but not of so very good quality like GPT2.
-  * https://jep-taln2020.loria.fr/wp-content/uploads/JEP-TALN-RECITAL-2020_paper_151.pdf Les modèles de langue contextuelsCAMEMBERTpour lefrançais : impact de la taille et de l’hétérogénéité des donnéesd’entrainement 08-19juin2020
-=====Pense bête pour NFS=====
-  * [[https://wiki.debian-fr.xyz/Partage_NFS|Partage NFS]]
-{{tag> ia python sb text_gen }}
+{{tag> ia python sb tal }}