Typos and small fixes
This commit is contained in:
parent
ef98b2cef9
commit
b6e5ebdbc9
|
@ -11,7 +11,7 @@ RUN apt-get update -y \
|
|||
&& apt-get install -y libglib2.0-0 libsm6 libxext6 libxrender-dev
|
||||
|
||||
# Install Miniconda
|
||||
RUN curl -so /miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh \
|
||||
RUN curl -Lso /miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh \
|
||||
&& chmod +x /miniconda.sh \
|
||||
&& /miniconda.sh -b -p /miniconda \
|
||||
&& rm /miniconda.sh
|
||||
|
|
|
@ -10,7 +10,7 @@ RUN apt-get update -y \
|
|||
&& apt-get install -y apt-utils git curl ca-certificates bzip2 cmake tree htop bmon iotop g++
|
||||
|
||||
# Install Miniconda
|
||||
RUN curl -so /miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh \
|
||||
RUN curl -Lso /miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh \
|
||||
&& chmod +x /miniconda.sh \
|
||||
&& /miniconda.sh -b -p /miniconda \
|
||||
&& rm /miniconda.sh
|
||||
|
|
|
@ -235,7 +235,7 @@ bash triton/scripts/run_server.sh
|
|||
To run in the foreground interactively, for debugging purposes, run:
|
||||
|
||||
```bash
|
||||
DAEMON="--detach=false" bash trinton/scripts/run_server.sh
|
||||
DAEMON="--detach=false" bash triton/scripts/run_server.sh
|
||||
```
|
||||
|
||||
The script mounts and loads models at `$PWD/triton/deploy/model_repo` to the server with all visible GPUs. In order to selectively choose the devices, set `NVIDIA_VISIBLE_DEVICES`.
|
||||
|
|
|
@ -29,5 +29,4 @@ ENV PYTHONPATH="/workdir/models/research/:/workdir/models/research/slim/:$PYTHON
|
|||
|
||||
COPY examples/ examples
|
||||
COPY configs/ configs/
|
||||
COPY qa/ qa/
|
||||
COPY download_all.sh download_all.sh
|
||||
|
|
|
@ -65,7 +65,7 @@ Other publicly available implementations of BERT include:
|
|||
[gluon-nlp](https://github.com/dmlc/gluon-nlp/tree/master/scripts/bert)
|
||||
[Google's official implementation](https://github.com/google-research/bert)
|
||||
|
||||
This model is trained with mixed precision using Tensor Cores on Volta, Turing, and the NVIDIA Ampere GPU architectures. Therefore, researchers can get results upto 4x faster than training without Tensor Cores, while experiencing the benefits of mixed precision training. This model is tested against each NGC monthly container release to ensure consistent accuracy and performance over time.
|
||||
This model is trained with mixed precision using Tensor Cores on Volta, Turing, and the NVIDIA Ampere GPU architectures. Therefore, researchers can get results up to 4x faster than training without Tensor Cores, while experiencing the benefits of mixed precision training. This model is tested against each NGC monthly container release to ensure consistent accuracy and performance over time.
|
||||
|
||||
### Model architecture
|
||||
|
||||
|
@ -76,7 +76,7 @@ BERT's model architecture is a multi-layer bidirectional transformer encoder. Ba
|
|||
|BERTBASE |12 encoder| 768| 12|4 x 768|512|110M|
|
||||
|BERTLARGE|24 encoder|1024| 16|4 x 1024|512|330M|
|
||||
|
||||
BERT training consists of two steps, pre-training the language model in an unsupervised fashion on vast amounts of unannotated datasets, and then using this pre-trained model for fine-tuning for various NLP tasks, such as question and answer, sentence classification, or sentiment analysis. Fine-tuning typically adds an extra layer or two for the specific task and further trains the model using a task-specific annotated dataset, starting from the pre-trained backbone weights. The end-to-end process in depicted in the following image:
|
||||
BERT training consists of two steps, pre-training the language model in an unsupervised fashion on vast amounts of unannotated datasets, and then using this pre-trained model for fine-tuning for various NLP tasks, such as question and answer, sentence classification, or sentiment analysis. Fine-tuning typically adds an extra layer or two for the specific task and further trains the model using a task-specific annotated dataset, starting from the pre-trained backbone weights. The end-to-end process is depicted in the following image:
|
||||
|
||||
![](data/images/bert_pipeline.png?raw=true)
|
||||
|
||||
|
|
|
@ -82,7 +82,7 @@ if __name__ == '__main__':
|
|||
cmd_train += ' ' + ' '.join(remainder)
|
||||
cmd_eval += ' ' + ' '.join(remainder)
|
||||
if flags.gpus is not None:
|
||||
cmd_train = f'CUDA_VISIBLE_DEVICES={",".join(map(str, range(flags.gpus)))} ' + cmd
|
||||
cmd_train = f'CUDA_VISIBLE_DEVICES={",".join(map(str, range(flags.gpus)))} ' + cmd_train
|
||||
|
||||
# print command
|
||||
line = '-' * shutil.get_terminal_size()[0]
|
||||
|
|
Loading…
Reference in a new issue