Masked Language Modelling (MLM) and Next Sentence Prediction (NSP) objectives from
BERT
.
Predicted masked-out tokens from an input sentence and whether a pair of sentences occur as neighbors in a document.
Training
We train for 100,000 steps with a global batch size of 4,096 sequences of a maximum length of 1,024 so that approximately 400B~tokens are observed. This takes roughly two days using 64 NVIDIA A100 GPUs.
Details about the model architecture are reported in the table below.
Hyperparameter
Value
Hidden size
768
Intermediate size
3072
Max. position embeddings
1024
Num. of attention heads
12
Num. of hidden layers
12
Attention
Multi-head
Num. of parameters
≈125M
Use
This model is trained on 86 programming languages from GitHub code including GitHub issues and Git Commits, and can be efficiently fine-tuned for both code- and text-related tasks.
We fine-tuned on a token classification task to detect PII and have released
StaPII
model.
Limitations
There are limitations to consider when using StarEncoder. It is an encoder-only model, which limits its flexibility in certain code generation or completion tasks,
and it was trained on data containing PII, which could pose privacy concerns. Performance may vary across the 80+ supported programming languages,
particularly for less common ones, and the model might struggle with understanding domains outside programming languages.
License
The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement
here
.
Runs of bigcode starencoder on huggingface.co
2.1K
Total runs
0
24-hour runs
195
3-day runs
-30
7-day runs
-472
30-day runs
More Information About starencoder huggingface.co Model
starencoder huggingface.co
starencoder huggingface.co is an AI model on huggingface.co that provides starencoder's model effect (), which can be used instantly with this bigcode starencoder model. huggingface.co supports a free trial of the starencoder model, and also provides paid use of the starencoder. Support call starencoder model through api, including Node.js, Python, http.
starencoder huggingface.co is an online trial and call api platform, which integrates starencoder's modeling effects, including api services, and provides a free online trial of starencoder, you can try starencoder online for free by clicking the link below.
bigcode starencoder online free url in huggingface.co:
starencoder is an open source model from GitHub that offers a free installation service, and any user can find starencoder on GitHub to install. At the same time, huggingface.co provides the effect of starencoder install, users can directly use starencoder installed effect in huggingface.co for debugging and trial. It also supports api for free installation.