Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
jinaai
/
xlm-roberta-flash-implementation
like
25
Follow
Jina AI
428
Transformers
94 languages
xlm-roberta
Inference Endpoints
License:
cc-by-nc-4.0
🇪🇺 Region: EU
Model card
Files
Files and versions
Community
56
Train
Deploy
Use this model
refs/pr/56
xlm-roberta-flash-implementation
10 contributors
History:
63 commits
michael-guenther
add option to output hidden states
681845d
11 days ago
.gitattributes
1.52 kB
initial commit
9 months ago
README.md
1.47 kB
Update README.md
2 months ago
block.py
17.8 kB
refine-codebase (#33)
4 months ago
configuration_xlm_roberta.py
6.54 kB
fix: set fp32 when using cpu bc bf16 is slow (#44)
3 months ago
convert_roberta_weights_to_flash.py
6.94 kB
Support for SequenceClassification (#7)
8 months ago
embedding.py
3.88 kB
refine-codebase (#33)
4 months ago
mha.py
34.4 kB
cpu-inference (#35)
4 months ago
mlp.py
7.62 kB
refine-codebase (#33)
4 months ago
modeling_lora.py
15.4 kB
[Fix bug] TypeError: argument of type 'XLMRobertaFlashConfig' is not iterable (#55)
23 days ago
modeling_xlm_roberta.py
51.1 kB
add option to output hidden states
11 days ago
rotary.py
24.5 kB
fix: update frequencies when updating the rope base value (#40)
4 months ago
stochastic_depth.py
3.76 kB
refine-codebase (#33)
4 months ago
xlm_padding.py
10 kB
refine-codebase (#33)
4 months ago
