Skip to content

[tokenizers] Upgrade huggingface tokenizers to 1.14.1 #2818

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 23, 2023
Merged

[tokenizers] Upgrade huggingface tokenizers to 1.14.1 #2818

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/workflows/native_s3_huggingface.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ jobs:
- name: Install Environment
run: |
yum -y update
yum -y install centos-release-scl-rh epel-release
yum -y install centos-release-scl-rh epel-release perl-core
yum -y install devtoolset-7 git patch cmake3 libstdc++-static
ln -s /usr/bin/cmake3 /usr/bin/cmake
curl https://sh.rustup.rs -sSf | sh -s -- -y
Expand Down Expand Up @@ -184,7 +184,7 @@ jobs:
- name: Install Environment
run: |
yum -y update
yum -y install centos-release-scl-rh epel-release
yum -y install centos-release-scl-rh epel-release perl-core
yum -y install devtoolset-7 git patch cmake3 libstdc++-static
ln -s /usr/bin/cmake3 /usr/bin/cmake
curl https://sh.rustup.rs -sSf | sh -s -- -y
Expand Down
2 changes: 1 addition & 1 deletion extensions/tokenizers/build.cmd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
@rem choco install rust -y
@rem choco install jdk8 -y

set VERSION=python-v"%1"
set VERSION=v"%1"

if exist "tokenizers" (
echo Found "tokenizers"
Expand Down
2 changes: 1 addition & 1 deletion extensions/tokenizers/build.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ elif [[ -n $(command -v sysctl) ]]; then
fi
PLATFORM=$(uname | tr '[:upper:]' '[:lower:]')

VERSION=python-v$1
VERSION=v$1
ARCH=$2

pushd $WORK_DIR
Expand Down
2 changes: 1 addition & 1 deletion extensions/tokenizers/rust/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ edition = "2018"

[dependencies]
jni = "0.19.0"
tokenizers = { path = "../tokenizers/tokenizers", version = "*" }
tokenizers = { path = "../tokenizers/tokenizers", version = "*", features = ["http"] }

[target.'cfg(target_os = "linux")'.dependencies]
openssl = { version = "0.10", features = ["vendored"] }
Expand Down
8 changes: 6 additions & 2 deletions extensions/tokenizers/rust/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -490,7 +490,7 @@ pub extern "system" fn Java_ai_djl_huggingface_tokenizers_jni_TokenizersLibrary_
}
}
let decoding: String = tokenizer
.decode(decode_ids, skip_special_tokens == JNI_TRUE)
.decode(&*decode_ids, skip_special_tokens == JNI_TRUE)
.unwrap();
let ret = env
.new_string(decoding)
Expand Down Expand Up @@ -527,8 +527,12 @@ pub extern "system" fn Java_ai_djl_huggingface_tokenizers_jni_TokenizersLibrary_
}
batch_decode_input.push(decode_ids);
}
let mut references: Vec<&[u32]> = Vec::new();
for reference in batch_decode_input.iter() {
references.push(reference);
}
let decoding: Vec<String> = tokenizer
.decode_batch(batch_decode_input, skip_special_tokens == JNI_TRUE)
.decode_batch(&references, skip_special_tokens == JNI_TRUE)
.unwrap();
let ret: jobjectArray = env
.new_object_array(batch_len, "java/lang/String", JObject::null())
Expand Down
2 changes: 1 addition & 1 deletion gradle.properties
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ trt_version=8.4.1
onnxruntime_version=1.16.0
paddlepaddle_version=2.3.2
sentencepiece_version=0.1.97
tokenizers_version=0.13.3
tokenizers_version=0.14.1
fasttext_version=0.9.2
xgboost_version=1.7.5
lightgbm_version=3.2.110
Expand Down