jinaai
/

xlm-roberta-flash-implementation

Inference Endpoints

🇪🇺 Region: EU

Model card Files Files and versions Community

xlm-roberta-flash-implementation

Commit History

fix: set fp32 when using cpu bc bf16 is slow

6787a0f
verified

jupyterjazz commited on Sep 25

Update modeling_lora.py

1b0fa28
verified

jupyterjazz commited on Sep 18

refactor-task-type-to-task (#43)

ffd672d
verified

jupyterjazz commited on Sep 16

Update modeling_xlm_roberta.py

b20a611
verified

jupyterjazz commited on Sep 11

Set normalize_embeddings to True

f2933ac
verified

jupyterjazz commited on Sep 11

fix: partition adapter mask when batch size is specified (#41)

c0215f6
verified

jupyterjazz commited on Sep 9

fix: update frequencies when updating the rope base value (#40)

8b2ad1e
verified

jupyterjazz commited on Sep 3

feat: update the readme

a6bb16f

nan commited on Aug 30

fix mixed precision loading with recent transformers versions (#39)

bda5e8d
verified

jupyterjazz commited on Aug 27

lora-instructions (#36)

a709b51
verified

michael-guenther

Jackmin108 commited on Aug 27

fix-device-issues (#38)

57dbe22
verified

Jackmin108 commited on Aug 26

fix: override use_flash_attn in lora

dc4080e
verified

jupyterjazz commited on Aug 26

Fix rotary backward

169b7fb
verified

jupyterjazz commited on Aug 23

cpu-inference (#35)

80b1ff7
verified

Jackmin108 commited on Aug 23

feat: configurable use_reentrant (#37)

09dbf45
verified

gmastrapas commited on Aug 22

refine-codebase (#33)

2646361
verified

jupyterjazz commited on Aug 16

fix-adapter-masks (#32)

0f0bed6
verified

Jackmin108 commited on Aug 12

change rotary base (#31)

4434bf3
verified

Jackmin108 commited on Aug 12

2-adapter-tuning (#29)

95fd08c
verified

Jackmin108 commited on Aug 12

Update modeling_xlm_roberta.py

027219a
verified

jupyterjazz commited on Aug 7

2-adapter-tuning-initial-impl (#30)

2cc8472
verified

Jackmin108 commited on Aug 7

Update modeling_xlm_roberta.py

3eceb33
verified

jupyterjazz commited on Aug 6

make-lora-stateless (#25)

e860caa
verified

jupyterjazz commited on Aug 5

feat-routing (#26)

6a92924
verified

makram93 commited on Aug 2

fix-rope-inference (#28)

955fea2
verified

jupyterjazz commited on Aug 1

no-flash-attention-during-inference (#22)

7ad815b
verified

jupyterjazz commited on Jul 23

Rename config to config.json

4d09ca8
verified

jupyterjazz commited on Jul 16

Create config

721e106
verified

bwang0911 commited on Jul 1

Delete config.json

a60f7c0
verified

bwang0911 commited on Jun 30

rope-embeddings (#20)

e3681c2
verified

jupyterjazz commited on Jun 6

alibi (#19)

ab85772
verified

Jackmin108 commited on Jun 4

lora bugfix (#16)

7c4a80c
verified

Jackmin108 commited on May 24

Update config.json (#15)

98c3cd2
verified

bwang0911 commited on May 21

Update tokenizer_config.json (#14)

c8da5f5
verified

bwang0911 commited on May 21

Update modeling_xlm_roberta.py (#13)

d230f23
verified

bwang0911 commited on May 20

Update modeling_xlm_roberta.py (#12)

64c81c6
verified

bwang0911 commited on May 20

truncate-embedding-dimension (#10)

8542ad8
verified

jupyterjazz commited on May 16

lora-multiple-adapters (#11)

27d23b2
verified

jupyterjazz commited on May 15

Refactor LoRA (#8)

4b000ec
verified

jupyterjazz commited on May 14

support lora (#1)

f9b3adb
verified

jupyterjazz commited on Apr 22

Support for SequenceClassification (#7)

0bb73e5
verified

michael-guenther commited on Apr 22

Support torch_dtype and CLS pooling (#6)

13c4251
verified

michael-guenther commited on Apr 19

Update modeling_xlm_roberta_for_glue.py

102e7bc
verified

koukandre commited on Apr 17

Create modeling_xlm_roberta_for_glue.py (#4)

4dd727d
verified

koukandre commited on Apr 17

add-encode-function (#5)

424df3c
verified

michael-guenther commited on Apr 17

support-cpu (#2)

290e593
verified

michael-guenther commited on Apr 17

Update configuration_xlm_roberta.py

807ba34
verified

jupyterjazz commited on Apr 16

Update configuration_xlm_roberta.py

9db6c6f
verified

jupyterjazz commited on Apr 16

add stochastic_depth

77af1c7

michael-guenther commited on Apr 15

support activation checkpointing

1c61b96

michael-guenther commited on Apr 12