263 Commits

Author SHA1 Message Date
GassiGiuseppe
b805dc538e learning sheduler as torch one 2025-10-08 16:05:22 +02:00
Christian Risi
c2e13bc9c6 Quick fix to architecture 2025-10-08 12:34:09 +02:00
GassiGiuseppe
14c3914571 Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder 2025-10-08 12:14:05 +02:00
Christian Risi
b9273b95e2 Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder 2025-10-08 12:13:46 +02:00
GassiGiuseppe
c263e2cf13 Custom learning rate sheduler from Attention is all you need 2025-10-08 12:13:02 +02:00
GassiGiuseppe
c9a50d50b7 typo in Batcher 2025-10-08 11:39:08 +02:00
GassiGiuseppe
9b0c57c238 Batcher ended, attention it returns list of tokenId, which later needs to be embedded 2025-10-08 11:26:47 +02:00
Christian Risi
24ea4d3ba4 Added a training model for NanoSocrates 2025-10-08 11:18:05 +02:00
GassiGiuseppe
e353c200d7 updated special token 2025-10-08 11:02:18 +02:00
GassiGiuseppe
159266a603 WIP Batcher added class to fourth task 2025-10-08 00:39:16 +02:00
GassiGiuseppe
7027414342 Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder 2025-10-07 23:16:20 +02:00
GassiGiuseppe
fc44929a7b moved spanned mask variables in init for better reliability, also tested 2025-10-07 23:15:50 +02:00
Christian Risi
0560bc439a Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder 2025-10-07 20:45:10 +02:00
Christian Risi
8adacdb08c Added new playgrounds 2025-10-07 20:45:04 +02:00
Christian Risi
533347ee22 Added new special token 2025-10-07 20:44:54 +02:00
Christian Risi
d1ff88da82 Added small dataset 2025-10-07 20:44:40 +02:00
Christian Risi
3f465991f0 Added toy dataset 2025-10-07 20:44:11 +02:00
GassiGiuseppe
96cbf4eabb wip Batcher 2025-10-07 20:09:51 +02:00
GassiGiuseppe
f801afe0e4 Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder 2025-10-07 17:42:21 +02:00
GassiGiuseppe
b4ee8362a2 WIP training Batching 2025-10-07 17:41:53 +02:00
Christian Risi
3021a51961 Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder 2025-10-07 16:38:12 +02:00
Christian Risi
99b5198c9a WIP 2025-10-07 16:38:08 +02:00
Christian Risi
b97282179d Fixed a bug about sequence normalizations 2025-10-07 16:37:43 +02:00
Christian Risi
fdece42462 Made model Batch ready 2025-10-07 16:37:20 +02:00
Christian Risi
109ad9f36b Changed Imports 2025-10-07 16:36:59 +02:00
Christian Risi
fef933da9d Added <PAD> and moved <END> Token 2025-10-07 16:36:45 +02:00
Christian Risi
c65f5e66fe Uploaded all playgrounds 2025-10-07 16:36:26 +02:00
Christian Risi
f9545aca1d Deleted MultiHeadAttention 2025-10-07 16:36:11 +02:00
GassiGiuseppe
490edcfd53 WIP Batcher 2025-10-07 15:36:51 +02:00
Christian Risi
9b5bb6d5f8 Added support for batches 2025-10-07 12:15:03 +02:00
GassiGiuseppe
14b810c451 WIP NanoSocratesEmbedder for batching 2025-10-06 21:41:45 +02:00
GassiGiuseppe
56d438f01a WIP NanoSocratesCore 2025-10-06 18:21:27 +02:00
GassiGiuseppe
745424a978 new special token for start sequence in decoder 2025-10-06 18:21:10 +02:00
GassiGiuseppe
e1549d4458 Modified decoder and decoder for sequential architecture 2025-10-06 18:20:46 +02:00
Christian Risi
456ce724fe Added capability of returning target after truncating 2025-10-06 17:43:01 +02:00
Christian Risi
44307cd917 Added util to create padding mask 2025-10-06 17:29:05 +02:00
Christian Risi
ffdb312d58 Added a util to create truncated RDF lists 2025-10-06 17:22:13 +02:00
Christian Risi
0007c38212 Added a util to make masked inference 2025-10-06 17:02:06 +02:00
Christian Risi
9c1043e0ba Added post tokenization utils 2025-10-06 17:01:18 +02:00
Christian Risi
ee8e56798c Added new utils 2025-10-06 17:00:55 +02:00
Christian Risi
1797571bb2 Added test to see if illegal tokens were included in target 2025-10-06 16:17:12 +02:00
Christian Risi
e93710af08 Fixed illegal tokens being added in target output 2025-10-06 16:16:47 +02:00
Christian Risi
d3bba9b944 Added actual test 2025-10-06 16:06:17 +02:00
Christian Risi
b1e7af0607 Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder 2025-10-06 15:55:44 +02:00
Christian Risi
d3b1f7da91 Added testing for spanned masking 2025-10-06 15:55:40 +02:00
Christian Risi
c217f5dec9 Added 2 types of masking 2025-10-06 15:45:45 +02:00
Christian Risi
49f0beb6ea Updated imports 2025-10-06 15:45:28 +02:00
GassiGiuseppe
05bb460999 file to test batch attention mask 2025-10-06 13:03:20 +02:00
GassiGiuseppe
948c3fd7ac update to batch attention mask 2025-10-06 13:03:03 +02:00
GassiGiuseppe
87409fecd5 added method fot batched attention_mask 2025-10-06 12:00:11 +02:00