allenai longformer issues

allenai / longformer

Longformer: The Long-Document Transformer

https://arxiv.org/abs/2004.05150

Apache License 2.0

2.05k stars 276 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Difference between this codebase and Huggingface?

#210 aleSuglia opened 3 years ago
0
Cannot build the docker image following the Cheatsheet.txt

#209 zheng-ningxin opened 3 years ago
0
What kind/format of text can replace your use of wikitext-103-raw-v1?

#208 jenka13all opened 3 years ago
0
LongformerForSequenceClassification explanation

#207 Nick9214 opened 3 years ago
1
Error when converting MBart to Longformer

#206 edgartanaka opened 3 years ago
2
Correct way of loading pretrained model led-base-16384

#205 kgarg8 opened 3 years ago
0
LongformerEncoderDecoder overshooting RAM: triggered OOM after training stably for 6-7 hours

#204 kgarg8 closed 3 years ago
1
Embedding dimension

#203 Nick9214 opened 3 years ago
0
Help needed with document/sentence embedding using longformer (LongformerForMaskedLM) model.

#202 pratikchhapolika opened 3 years ago
0
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [12, 4096, 1]], which is output 0

#201 Herais closed 3 years ago
1
Update longformer.py

#200 Herais closed 3 years ago
0
The availability of Longformer-tiny?

#199 songhwanjun opened 3 years ago
0
Reproducibility of Table 11 (Summarization)

#198 fengwang99feng opened 3 years ago
0
Gradio Web Demo

#197 AK391 opened 3 years ago
0
first commit

#196 aliebrahiiimi closed 3 years ago
0
cannot import name 'nvcc' from 'tvm.contrib' (unknown location)

#195 wsmzzz opened 3 years ago
4
Confusing attention_window configuration in converting roberta-base to longformer notebook

#194 181847 opened 3 years ago
0
Run inference for summarization

#193 jacob-parnell-rozetta opened 3 years ago
1
allenai `LongformerEncoderDecoderForConditionalGeneration` vs huggingface `LEDForConditionalGeneration`

#192 EmilyAlsentzer opened 3 years ago
4
Convert BERT to "long" version

#191 dawei-yu opened 3 years ago
5
CUDA out of memory with a paragraph of length 3000

#190 SefaZeng closed 3 years ago
2
reproductivity of the output of Longformer

#189 passenger20 opened 3 years ago
2
imbalanced classification during evidence extraction of HotpotQA

#188 Fan-Luo closed 3 years ago
2
IndexError: index out of range in self

#187 BinchaoPeng opened 3 years ago
1
Longformer model with weight(model.encoder.embed_positions.weight) error

#186 BinchaoPeng opened 3 years ago
3
about the model name

#185 BinchaoPeng opened 3 years ago
0
Memory requirement changes after converting a model using create_long_model() function

#184 taufique74 opened 3 years ago
0
infer speed longformer vs bert

#183 SuMeng123 opened 3 years ago
0
about global attention some issue

#182 yysirs opened 3 years ago
0
Repeated and missed id of hyperpartisan splits

#181 tsupei opened 3 years ago
1
local vs global attention in further MLM pre-training.

#180 chrisvdwerf opened 3 years ago
3
Long T5

#179 HaokunLiu opened 3 years ago
0
The exact English pretraining data and Chinese pretraining data that are exact same to the BERT paper's pretraining data.

#178 guotong1988 opened 3 years ago
0
Size mismatch error - LongBART

#177 amoramine opened 3 years ago
1
Compile tvm kernel in newer version of CUDA

#176 elb3k closed 2 years ago
1
longformer speed compared to bert model

#175 gkim89 opened 3 years ago
1
ValueError: hidden size is called d_model

#174 leopardv10 opened 3 years ago
0
GPUs requested but none are available.

#173 Behnam-Taki opened 3 years ago
0
MBART into LongMBART

#172 Dmitriuso closed 3 years ago
0
longformer infer speed?

#171 lookmyeye opened 3 years ago
3
Urgent plz! Sequence Classifier produces same output during prediction

#170 MarwaEssam opened 3 years ago
1
Update convert_model_to_long.ipynb

#169 SergeyShk opened 3 years ago
0
fix the docker problem; a new way to compute the case when t1 is diagonaled and transposed

#168 pzzhang opened 3 years ago
0
Instructions to compile the TVM CUDA kernel do not work

#167 pzzhang opened 3 years ago
1
Update conversion script to transformers v4.2.0

#166 adamwawrzynski closed 1 year ago
1
Initializing Weights

#165 MarwaEssam opened 3 years ago
3
Generating Embeddings

#164 MarwaEssam opened 3 years ago
1
index out of range in self!

#163 MarwaEssam opened 3 years ago
6
when fine-turn on QuacQA dataset,I meet RuntimeError: index out of range: Tried to access index 1 out of table with 0 rows. at /pytorch/aten/src/TH/generic/THTensorEvenMoreMath.cpp:418

#162 Antlerkeke opened 3 years ago
1
fix instructions to load triviaqa checkpoint #134

#161 antoniogois opened 3 years ago
0

Previous Next