-
Every time I try to run the generate.py script from the Git Repo it throws this error. The stack trace is pretty simple :
---------------------------------------------------------------------------
…
-
您好~想请问一下您在附录中有关IMDB情感分类数据集的实验细节。因为数据集中对每个query只包含单条样本,我们尝试使用imdb-gpt2进行采样扩充出另一条样本,可是效果不是很理想,所以想请问一下您是如何构建RRHF的训练样本对的呢
祝好~:)
-
**Is your feature request related to a problem? Please describe.**
No, it's not a problem but a feature request
**System information**
- ONNX Runtime version (you are using): 1.9
**Describe th…
-
Hello, I want to fine-tune the prefix along with the whole BART model.
And I comment the freeze code in [`seq2seq/finetune.py#L95`.](https://github.com/XiangLi1999/PrefixTuning/blob/6519d30e69b15a180…
-
Currently, we have the following schedule operations logic for gpt2.
```python3
# code snippet from slapo/model_schedule/gpt2.py
...
attn_op = []
for idx in range(model_config.num_hidde…
-
### System Info
- `transformers` version: 4.40.0.dev0
- Platform: Linux-5.4.0-166-generic-x86_64-with-glibc2.29
- Python version: 3.8.10
- Huggingface_hub version: 0.20.2
- Safetensors version: 0…
-
### Model description
The translation model m2m100 proposed by Facebook is too huge to train using DDP, is there any open solution for model parallelism of m2m100, just like GPT2? Thank you.
### Ope…
-
I trained the PPO model, use the gpt. I modified the option of model_name_or_path from opt to gpt2 I passed step 1 and step 2,But An error occurred in step 3.The error is as follows:
╭────────────…
-
I trained the PPO model, use the gpt. I modified the option of model_name_or_path from opt to gpt2 I passed step 1 and step 2,But An error occurred in step 3.The error is as follows:
╭────────────…
-
Hi Eric, I'm looking at your paper for a school project and was wondering if you had any tips for adapting the code to generate triggers for a BERT model during the sst attack. Any help would be appre…