-
### Feature request
As what we have with `TFBertTokenizer`, but with models that use Byte Pair Encoding (e.g. `TFT5Tokenizer`, `TFClipTokenizer`) etc...
They were implemented in `keras-nlp` (https…
-
After https://github.com/robotology/gz-sim-yarp-plugins/pull/195, these two tests still fail non deterministically. This issue track fixing this flaky failures.
-
### System information
- **OS version/distro**: macOS 10.15
- **.NET Version (eg., dotnet --info)**: 3.1.301
### Issue
- **What did you do?**
I would like to use the PredictionEnginePool …
-
HI Guillaume,
This is an amazing repo - great work!
found a minor error -
estimator.export_saved_model('saved_model', serving_input_receiver_fn) -> estimator.export_savedmodel
Keep up …
-
Hi,
I was curious if seamless integration with TF Serving is on the roadmap?
I see that there is support for remote models here [remote_model.py](https://github.com/PAIR-code/lit/blob/main/lit_n…
-
*********************************************
温馨提示：根据社区不完全统计，按照模板提问，可以加快回复和解决问题的速度
*********************************************
## 环境
- 【FastDeploy版本】： fastdeploy:1.0.7-gpu-cuda11.4-trt8.5-21…
tianv updated
4 months ago
-
The provided datasets have four variants, each serving a specific purpose, and contain a `text_description` as described below E.g gov:
1. **syntheticDocQA_government_reports_test** – **No text_des…
-
The bandits statlog Vowpal wabbit example is not able to load the model at the step
bandits_experiment.deploy_model(model_id=bandits_experiment.last_trained_model_id)
Here is trace:
algo-1-y…
tvkpz updated
4 years ago
-
## Environment
OS Version: Ubuntu Jammy
* Source or binary build?
```
ign launch --version
5.3.0
```
## Description
* Expected behavior: Websocket server starts and allows for connection to …
-
To make these models useful for serving we should have some export support.