Bot releases are hidden (Show)
Published by jeswan over 3 years ago
We refactored jiant
to make it easier to add a Transformers-style model to the library. Please see the guide to add a model for more details. We added DeBERTa V2 as part of these changes.
The simple API now uses hf_pretrained_model_name_or_path
instead of model_type
as an argument. hf_pretrained_model_name_or_path
is used as an input to Hugging Face's Auto Classes.
de5437a Merge easy_add_model feature branch (#1309)
56ceae5 Updating notebooks, removing model_type (#1270)
723786a Switch export_model to use AutoModel and AutoTokenizer (#1260)
84f2f5a Adding Acceptability judgment and SentEval tasks (#1271)
f796e5a improve robustness of the simple runscript (#1307)
4d0f6a9 Add test matrix (#1308)
ee65662 Update README.md
65888b4 Benchmark script fixes (#1301)
b4b5de0 Assert spans <= max_seq_len (#1302)
5ba72f7 axg->axb fix (#1300)
235f646 MNLI diagnostic example bug (#1294)
4ab0c08 Bump lxml from 4.6.2 to 4.6.3 (#1304)
741ab09 Documentation + cleanup (#1282)
dbbb4e6 export_model tweak (#1277)
Published by jeswan almost 4 years ago
e9d6c68 Adding download code for ARCT, MCTest, MCTACO, MuTual, and QuAIL (#1258)
a88956a Add edge probing notebook (#1261)
d5e3b2e Prevents computing loss in multigpu when not available (#1257)
9cfe644 Truncate MCQ inputs from the start and not end (#1256)
33c4a26 Bump lxml from 4.5.1 to 4.6.2 (#1263)
9a45712 Add test for export_model (#1259)
Published by jeswan almost 4 years ago
1ab34a4 Adding ROPES, RACE tasks (#1234)
ce62495 Add simple save model test + fix (#1227)
e5fbea4 fix create examples wsc (#1247)
605d794 committing quail fix (#1249)
192d6b5 Namespace default cache dir by model_type. (#1246)
Published by jeswan almost 4 years ago
838cdd2 SQuAD tokenization update (#1232)
5329c7e Winogrande Task Property (#1229)
50b0116 Further fix for encoder_only (#1242)
1f66050 Allow force_overwrite
to override "done" condition (#1241)
59438ed change checkpoint save default (#1233)
e2e85c9 guids_fix (#1225)
74c6ba0 fix notebooks path (#1231)
18c41fc Load only encoder weights (#1240)
711c6c8 Introduction filename correction (#1239)
f340d04 minor typo fix (#1238)
Published by jeswan almost 4 years ago
e4f1c4b Winogrande (#1203)
e7eefc6 Fever NLI task and data downloader (#1215)
cb601cf Quail (#1208)
c00360f MCTest and MCTACO (#1197)
76e2826 Mcscript Task Property (#1219)
9892766 Add docs for adding tasks to data downloader (#1221)
cb7ee4a Fix save-last behavior (#1220)
0cc8cbb use task_name instead of task.name (#1224)
Published by jeswan almost 4 years ago
442a2b0 - piqa (#1216) (William Huang)
c535e78 - Natural Questions (MRQA), NewsQA, Quoref (#1207) (Jason Phang)
d1b14c1 - mcscript (#1152) (William Huang)
da7550d - Adding arc_easy, arc_challenge, mutual, mutual_plus (#1206) (yzpang)
f4bca4e - add arct task doc documentation (#1154) (jeswan)
b23c0f7 - arct (#1151) (William Huang)
58beb8f - anli download (#1147) (Jason Phang)
0b3dff5 - Adding ability to resume run in Simple API (#1205) (Jason Phang)
b81254b - Fix git clone in example notebooks (#1155) (jeswan)
aa4d111 - Bugfix for single-task configurator (#1143) (Jason Phang)
14fac1c - Fix colab link in README (#1142) (Jonathan Chang)
02bb070 - setup.py fix (#1141) (Jason Phang)
7d1cc29 - Adding SingleTaskConfigurator, some cleanup (#1135) (Jason Phang)
bump torch>=1.5.0. bump transformers==3.1.0. notebook installation switched to local pip install. (#1218) (jeswan)
b20f30a - resolve_is_lower_case fix (#1204) (Jason Phang)
5724fee - Adjust case for span prediction (#1201) (Jason Phang)
c3387a3 - nlp to datasets (#1137) (Jason Phang)
04bbb39 - update issue numbers from jiant-dev to jiant transfer (#1196) (jeswan)
392976c - Task tweaks (#1149) (Jason Phang)
82ed396 - use hidden_size (#1148) (Jason Phang)
Published by zphang about 4 years ago
jiant
2.0 is a complete rewrite of jiant
, built natively on transformers
and nlp
/datasets
Published by pyeres over 4 years ago
Published by pyeres over 4 years ago
Published by pyeres over 4 years ago
Published by sleepinyourhat about 5 years ago
Minor changes:
Published by sleepinyourhat about 5 years ago
Highlighted changes:
pytorch_transformers
1.2.main.py
and the config
directory to accomodate that change).Minor changes:
pytorch_transformers
.Dependency changes:
pytorch_transformers
to 1.2.0.Published by sleepinyourhat about 5 years ago
We expect another release within a week or two that will add support for RoBERTa (see #890), but this is a quick intermediate release now that XLNet support is stable/working.
Highlighted changes:
max_vals
is now used when computing warmup time with optimizers that use warmup.auto
option for tokenizer chooses an appropriate tokenizer for any given input module.<SOS>
/<EOS>
/[SEP]
/[CLS]
tokens are handled during task preprocessing. This will require small changes to custom task code along the lines of what is seen in #845.Dependency changes:
Warnings:
Published by sleepinyourhat over 5 years ago
Bug fixes:
Published by pruksmhc over 5 years ago
The first stable release of jiant
.
Highlighted changes:
Dependency changes:
Warnings:
Published by W4ngatang over 5 years ago
This release contains code to recreate part of the experiments from the paper "Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling". For the remaining experiments, see this branch.
Published by pruksmhc over 5 years ago
A release with fixes to SuperGLUE baseline scripts/configurations.
Published by sleepinyourhat over 5 years ago
The initial work-in-progress release coinciding with the launch of SuperGLUE.
We currently support two-phase training (pretraining and target task training) using various shared encoders, including:
We also have support for SuperGLUE baselines, sentence encoder probing experiments, and STILTS-style training.
They can be found in https://github.com/nyu-mll/jiant/tree/master/config/examples
Published by sleepinyourhat about 6 years ago