-
### System Info
lorax:latest
### Information
- [X] Docker
- [ ] The CLI directly
### Tasks
- [X] An officially supported command
- [ ] My own modifications
### Reproduction
@tga…
-
We could start testing small models like gpt2-small-alpacaGPT4-epochs-5 for example
suoko updated
3 months ago
-
HF tokenizers/model loading take a frankly absurd amount of time to load (10s on my macbook)
It's often 80%+ of test time.
dlwh updated
8 months ago
-
Run generate_ Outputs_ Gpt2. py, the following error will occur:
../aten/src/ATen/native/cuda/Indexing.cu:1292: indexSelectLargeIndex: block: [624,0,0], thread: [32,0,0] Assertion `srcIndex < srcSele…
-
### System Info
latest transformers
### Who can help?
@ArthurZucker
### Information
- [ ] The official example scripts
- [x] My own modified scripts
### Tasks
- [ ] An officiall…
-
### 🐛 Describe the bug
```
import argparse
import math
from typing import Any, List, Union
import evaluate
import torch
import torch.distributed as dist
from data import GLUEDataBuilder
f…
-
INT8 quantized GPT2-Large is showing low performance compared to baseline fp32 performance.
-
HI all
I am a beginner and small question for this field.
I followed the readme and tried to run the study as per the default cofig.yaml. However, I got an error that the GPT2 model does not exist…
-
I am encountering an issue when trying to load a custom merged GPT2 tokenizer using GPT2TokenizerFast. Despite ensuring that the tokenizer.json file is correctly formatted, I receive the following err…
-
**Describe the bug**
Exporting a `gpt2` model using the provided `convert_to_onnx` script using `GPT2LMHeadModel_NoPadding` and both `--use_external_data_form` and `--optimize_onnx` flags, results in…