-
### System Info
```shell
Optimum 1.5.1
Transformers 4.25.1 (the training was fine for 4.24.0)
```
### Who can help?
@JingyaHuang
### Information
- [X] The official example scripts…
-
### Feature request
it would be nice to support feature extraction of batched input for GPT-style models using `Pipeline`s
### Motivation
I'm currently trying to generate encodings of a large numbe…
-
-
-
**Describe the bug**
We are seeing the following error when using the [ONNX Model optimizer](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/python/tools/transformers#model-optimizer…
-
Hi folks,
I followed the tutorial from https://www.deepspeed.ai/tutorials/inference-tutorial/#end-to-end-gpt-neo-27b-inference and wrote below code to run gpt2-xl inference.
```
import os
imp…
-
Hi This is a very interesting work. I am curious whether I could set multi-GPUs to train the model as the original Alpaca did?
-
### System Info
```shell
Optimum: 1.5.1
Python: 3.10.4
Platform: Windows 10
Cuda: 11.6
```
### Who can help?
@JingyaHuang @echarlaix
### Information
- [X] The official example scripts
- [ ] …
-
### 🐛 Describe the bug
My transformers inference script is running successfully in device CPU, but when using device MPS in MacOS M1 Pro, it will report 'aten::cumsum.out' op is missing, so I set env…
-
**Describe the bug**
Responses for transformers models are not relevant with long inputs and batch size > 1. This issue is related to gpt-like models, while this [issue](https://github.com/microsoft/…