Go
Home
Pricing
FAQ
Install
Home
Pricing
FAQ
Install
Login
via GitHub
younesbelkada/transformers
Pull Requests
Commits
circular-reference-schedulers
19445-fix
adapters
add_accelerate_roberta
add_bart_accelerate
add_bert_accelerate
add_better_transformers
add_bloom_flax
add_bloom_for_qa
add_bt_pipeline
add_dpt_hybrid
add_dpt_hybrid_2
add_esm_accelerate
add_flan_t5_doc
add_m2m100_accelerate
add_owl_vit_accelerate
add_roberta_accelerate
add_switch_transformers
add_vit_accelerate
add_whisper_accelerate
add-awq-fused
add-badam
add-blip
add-blip2-accelerate
add-blip2-int8
add-bt-doc
add-cache-api
add-cogvlm
add-dpt-hybrid-support
add-dtype-fe
add-dtype-precision-processor
add-efficient-sam-clean
add-exllama-v2-depre
add-falcon-h1
add-flash-attn-2
add-galore-optimizer
add-gguf-convert-trainer
add-llava-sdpa
add-marian-mt-accelerate
add-mobile-sam
add-mp-tests
add-no-split-modules
add-owl-vit-accelerate-support
add-peft-pipeline-pox
add-pix2struct
add-pix2struct-2
add-pix2struct-pipeline
add-sgalgn
add-super-resolution-pipeline
add-torch-dtype
add-torch-fp18
add-trainer-error-8bit
add-umt5
benchmark
better-tf-examples
bigscience176b
bigscience176b-jz
bigscience176b-test-fused
bigscience-jz-176-ds
bit-remove-unused-func
blip-2-accelerate
blip-fix-tolerance
blip-support-training
blip-text-refactor-test
bloom-change-slow-test
bloom-docstring
bloom-enhance-doc
bloom-fix-attn-mask
bloom-fix-module-order
bloom-fix-sequential-order
bloom-fix-tokenizer
bloom-minor-fix-tests
bnb_add_custom_map
bnb_add_safety_checker
bnb_simplify_test
bnb-add-mem-efficient
bnb-fix-change-arg-name
bnb-fix-cls-bug
bnb-fix-doc
bnb-fix-slow-test
bnb-fix-small-details
bnb-warn-device
ci_tweaks
circular-reference-schedulers
cleaner-pt-tf-conversion
cli
cohere-diff
ctrl-tokenizer-standardize
cvt-fix-init
denim-capybara-22
distil-update
distill-bloom
documentation
dpt-flax-younes
enable-input-require-grad
experiments-static-cache
extract-cached-archives
fast-tokenizers
finish-cogvlm
fipt-doctest
fix_codegen_causal_mask
fix_head_masking
fix_pt_tf_loading
fix_redirected_downloads
fix_redirected_link
fix_redirections
fix_t5_fp16
fix-4bit-blip2
fix-2042
fix-awq-tests
fix-beit-nit
fix-bert-pipeline
fix-bit-fp16
fix-bli-doctest
fix-blip2-accelerate
fix-blip-doctest
fix-blip-text-docstring
fix-bloom-deepspeed
fix-bloom-pipeline-test
fix-bnb-error-message
fix-bnb-itemize
fix-bnb-peft
fix-bnb-serialization-2
fix-bnb-slow-test
fix-bnb-trainer-test
fix-correct-dtype-casting
fix-documentation-warnings
fix-esm-accelerate
fix-fa-2-bf16
fix-fix-copies-2
fix-fm-rms
fix-fp16-generate
fix-fsmt
fix-fsmt-compatibility
fix-fuyu-nit
fix-gc-opt
fix-gc-recent
fix-gc-use-reentrant
fix-geb-fp16
fix-generation-doc
fix-gpt2-finetuning-memory
fix-gpt-neo-multi-gpu
fix-gpt-neo-x
fix-hubert-doctest
fix-idefics-config
fix-import-2
fix-improt
fix-int8-conversion
fix-int8-docstrin
fix-int8-seqtoseq
fix-integrations
fix-japanese-readme-template
fix-last-test-vith
fix-mbart
fix-mistral-regex
fix-mistral-training-bug
fix-mobilenet-v2-auto
fix-module-fp32
fix-nllb-device
fix-opt-bias
fix-opt-nit
fix-peft-device
fix-perceiver-test
fix-slow-path
fix-slow-tests
fix-spaces-token-issue
fix-speech-doctest
fix-switch-slow
fix-t5-dtype
fix-tf-xlm
fix-tf-xlnet
fix-tfroberta
fix-tok-pipe
fix-training-quanti
fix-ved-doctest
fix-vision-config
fix-vit-hybrid-test
fix-xlm-roberta
flash-att-2-temp
flava-docs
flax-tp-inference
fp4-bnb
generation_sampler
hf-quantizer-work
ignored-index-coherence
image-fp16
improved-generation
improved-testing
int8-config
int8_with_accelerate
integration-8bit
integration-8bit-codegen-hotfix
main
main-temp
master
mbart-fix-jit-issue
mini-fix-hqq
mistral-static-kv-cache
modify_distill_bert_module_name
opt_branch/opt-350-m
opt-350
opt-fix-device
opt-fix-mask
opt-fix-softmax-debug
opt-flax-tf
patch-bit
peft-fix-multi-adapter
peft-integration
pipelines-issues
pix2struct-cross-attn
pix2struct-refactored-ip
plugin-v1
potential-fix-ewkv
question-answering
quickstart-model2model
rbert
refactor-workflows
roberta-no-token-types
roc_bert_fix
run_language_modeling
scripts-device-flag
serialize-8bit
serving_improvements
shape_list
skip-multimodal-pipeline
small_fix_realm
switch_backup
t5-parallelism
temp-2
tentative-pipeline-t5
test_bnb_training
test-static-kv-cache
test-younes-workflow
tf
tf2-extended
tf2-glue
tokenizers
tokenizers-v2
torchhub
tpu-experiments
trainer-model-parallel
trocr-fix-use-cache
uncompressed_storage
update-deps
upgrade-run-generation
vilt-accelerate-suuport
vit-fix-init-nit
vqgan
xnli
younes/patch-bit-3
WIP closure instead of subclass
rlouf
committed
6 years ago
2c6ebf1a
unpack summaries
rlouf
committed
6 years ago
a8cf4a4f
pass pad token to mask builder
rlouf
committed
6 years ago
27a281cb
print loss
rlouf
committed
6 years ago
717c9d8c
specify tensor device in beam search
rlouf
committed
6 years ago
ca9b6f32
tweaks to the BeamSearch API
rlouf
committed
6 years ago
dae4df95
Share pre-trained embedding with the randomly initialized decoder
rlouf
committed
6 years ago
15a7edd4
fix eval
rlouf
committed
6 years ago
5c202cd8
add pyrouge requirement
rlouf
committed
6 years ago
5570486c
create new generate module
rlouf
committed
6 years ago
f33fb25c
finalize BS + tests
rlouf
committed
6 years ago
bac3e63f
update masks during beam search
rlouf
committed
6 years ago
533228af
end
rlouf
committed
6 years ago
c2708557
use BeamSearch + evaluate on ROUGE
rlouf
committed
6 years ago
5a06910a
test and fix removal of repeating 3-grams
rlouf
committed
6 years ago
4eb87588
test min_length & max_length constraints in Beam Search
rlouf
committed
6 years ago
1f52a892
test on minimum length and beam termination pass
rlouf
committed
6 years ago
cabcf152
WIP - <3 <3 Beam Search <3 <3
rlouf
committed
6 years ago
9983c1d0
load the pretrained weights for encoder-decoder
rlouf
committed
6 years ago
cd478c35
allow to save checkpoint on keyboard interrupt
rlouf
committed
6 years ago
aa24121e
update function to add special tokens
rlouf
committed
6 years ago
9b30045c
Add RoBERTa-based GPT-2 Output Detector from OpenAI
julien-c
committed
6 years ago
1c542df7
Fix other PyTorch models
julien-c
committed
6 years ago
2f3a4210
Fix BERT
julien-c
committed
6 years ago
d5319793
[tests] Flag to test on cuda
julien-c
committed
6 years ago
27e015bd
[tests] get rid of warning
julien-c
committed
6 years ago
13d9135f
[run_tf_glue] Add comment for context
julien-c
committed
6 years ago
f88c104d
misc doc
julien-c
committed
6 years ago
30968d70
Updating docblocks in optimizers.py
Dom Hudson
committed
6 years ago
de890ae6
GPT-2 XL
LysandreJik
committed
6 years ago
d7d36181
Older